US11468293B2 - Simulating and post-processing using a generative adversarial network - Google Patents
Simulating and post-processing using a generative adversarial network Download PDFInfo
- Publication number
- US11468293B2 US11468293B2 US16/714,103 US201916714103A US11468293B2 US 11468293 B2 US11468293 B2 US 11468293B2 US 201916714103 A US201916714103 A US 201916714103A US 11468293 B2 US11468293 B2 US 11468293B2
- Authority
- US
- United States
- Prior art keywords
- processor
- noise
- parameter
- sample
- generator
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active, expires
Links
Images
Classifications
-
- G06N3/0454—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N10/00—Quantum computing, i.e. information processing based on quantum-mechanical phenomena
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/047—Probabilistic or stochastic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
Definitions
- This disclosure generally relates to systems, devices, and methods for simulating and post-processing samples generated by a hybrid computing system comprising a quantum computer and a digital computer. Simulating and post-processing samples can include using machine learning techniques such as generative adversarial networks.
- a quantum processor is a computing device that can harness quantum physical phenomena (such as superposition, entanglement, and quantum tunneling) unavailable to non-quantum devices.
- a quantum processor may take the form of a superconducting quantum processor.
- a superconducting quantum processor may include a number of qubits and associated local bias devices, for instance two or more superconducting qubits.
- An example of a qubit is a flux qubit.
- a superconducting quantum processor may also employ coupling devices (i.e., “couplers”) providing communicative coupling between qubits. Further details and embodiments of exemplary quantum processors that may be used in conjunction with the present systems and devices are described in, for example, U.S. Pat. Nos. 7,533,068; 8,008,942; 8,195,596; 8,190,548; and 8,421,053.
- a quantum processor may include a topology that comprises a set of qubits and a set of couplers. Pairs of qubits can be communicatively coupled to one another via a respective coupler. Programmable elements such as digital-to-analog converters can be used to apply a bias to a qubit.
- a computational system comprising a quantum processor designed as such can find minimum-cost solution to an Ising minimization problem. Given a collection of biases and couplings, values from ⁇ 1, +1 ⁇ are assigned to spin variable s so as to minimize the energy function expressed as:
- E ⁇ ( s ) ⁇ i h i ⁇ s i + ⁇ i , j J i , j ⁇ s i ⁇ s j
- h i local biases
- J i,j coupling strengths.
- the spin variables can be interpreted as magnetic poles in a physical particle system and the optimal solution can be called a ground state.
- a flux signal may be applied to a respective qubit loop to realize the bias term h i of the Ising model. These flux signals also provide the spin variable terms s in the Ising model.
- a flux signal may be applied to a coupler that communicatively couples a pair of qubits to realize the J i,j term(s) in the Ising model.
- Adiabatic quantum computation typically involves evolving a system from a known initial Hamiltonian (the Hamiltonian being an operator whose eigenvalues are the allowed energies of the system) to a final Hamiltonian by gradually changing the Hamiltonian.
- a simple example of an adiabatic evolution is a linear interpolation between initial Hamiltonian and final Hamiltonian.
- H e (1 ⁇ s ) H i +sH f
- H i the initial Hamiltonian
- H f is the final Hamiltonian
- H e is the evolution or instantaneous Hamiltonian
- s is an evolution coefficient which controls the rate of evolution.
- Machine learning relates to systems and methods that can learn from data and make predictions based on data.
- machine learning can include deriving a model from example inputs (such as a training set) and then making data-driven predictions.
- a machine learning model can include methods for training a multilayer perceptron or neural network.
- a typical approach to designing part of a machine learning model can include applying an activation function to a weighted sum of input variables to determine an output.
- the activation function can be updated by adjusting a set of weights.
- a gradient can be calculated that captures the error of the output measured against a target distribution. The gradient can be used to back-propagate the error through each layer of the multilayer perceptron to adjust the set of weights.
- Generative learning and discriminative learning are two categories of approaches to machine learning. Generative approaches are based on models for a joint probability distribution over the observed and the target variables, whereas discriminative approaches are based on models for a conditional probability of the target variables given the observed variables. Examples of generators include Restricted Boltzmann Machines, Gaussian mixture models, and probabilistic context-free grammars. Some examples of generative learning models are described in PCT Publication No. WO02017132545A1.
- a sample is a subset of a population, such as a plurality of data points collected from a statistical population.
- a hybrid computer can draw samples from an analog computer acting as a sample generator.
- the analog computer can be operated to provide samples from a probability distribution, where the probability distribution assigns a respective probability of being sampled to each data point in the population.
- An analog processor such as a quantum processor, and in particular a quantum processor designed to perform quantum annealing and/or adiabatic quantum computation, may be operated as a sample generator, where the population can be possible states of the processor, and each sample can correspond to a state of the processor.
- Using an analog processor as a sample generator may be a preferred mode of operating the processor for certain applications.
- Operating an analog processor as a sample generator may also enable a broader range of problems to be solved compared to, for example, using an analog processor to find a low energy state of a Hamiltonian that encodes an optimization problem.
- Sampling from a quantum Hamiltonian can be challenging.
- the statistical nature of quantum processor such as one implemented in an adiabatic quantum computer, can be exploited for sampling purposes.
- Generating samples from a quantum processor can be computationally expensive, therefore it is desirable to combine the use of a quantum processor performing quantum annealing with the use of a classical or digital processor performing classical methods.
- One way to combine the use of a quantum processor and a classical or digital processor is to use post-processing techniques, such as described in PCT Patent Publication No. WO2016/029172A1.
- post-processing techniques such as described in PCT Patent Publication No. WO2016/029172A1.
- the amount of post-processing needed to achieve a desired accuracy can become large enough that it at least partially negates the benefit of obtaining initial samples from the quantum processor.
- An approach for improving sampling techniques from a quantum processor includes applying machine learning methods, such as generative adversarial networks, to simulate and/or post-process samples generated by the quantum processor.
- a method of computationally efficiently producing sample sets in a processor-based system may be summarized as including: initializing a generator parameter ⁇ ; initializing a discriminator parameter ⁇ ); drawing a noise sample z k from a noise prior distribution r(z); for each respective noise sample z k drawn from the noise prior distribution r(z), drawing a generated sample x (m
- z); drawing a target sample ⁇ circumflex over (x) ⁇ (k) from a target distribution h,J that was generated by a quantum processor for a set of biases h and a set of coupling strengths J, where k 1, . . . , K; adjusting the generator parameter ⁇ ; adjusting the discriminator parameter ⁇ ; and determining whether the adjusted generator parameter ⁇ and the adjusted discriminator parameter ⁇ each meet respective optimization criteria.
- the method may further include: receiving the set of biases and the set of coupling strength values before drawing the noise sample z k from the noise prior distribution r(z).
- the method may further include: in response to a determination that at least one of the adjusted generator parameter ⁇ or the adjusted discriminator parameter ⁇ do not meet the respective optimization criteria, drawing a new noise sample z k from the noise prior distribution r(z).
- the method may further include: in a first iteration, receiving a set of biases and a set of coupling strength values before drawing the noise sample from the noise prior distribution r(z); in response to a determination that at least one of the adjusted generator parameter ⁇ or the adjusted discriminator parameter ⁇ do not meet the respective optimization criteria, in a second iteration: receiving a new set of biases and a new set of coupling strength values before drawing a new noise sample in the second iteration; and drawing the new noise sample z k from the noise prior distribution r(z) in the second iteration.
- Drawing a noise sample z k from a noise prior distribution r(z) may include drawing a noise sample z k from a uniform distribution or a Gaussian distribution.
- Drawing a noise sample z k from a noise prior distribution r(z) may include drawing a noise sample z k from a multi-dimensional distribution.
- the method may further include generating a generated sample x for each noise sample z k drawn from noise prior distribution r(z) via a generator function g ⁇ (x
- z) determines a pointwise probability q ⁇ (x) of a generative distribution ⁇ defined by: q ⁇ ( x ) ⁇ z g ⁇ ( x
- the method may further include generating M generated samples x (m
- k) being a respective vector of qubit states defined on ⁇ 1,1 ⁇ n , where m 1, . . . , M.
- the method may further include: conditioning at least one of the generator or the discriminator on multiple sets of biases and multiple sets of coupling strengths.
- the method may further include: employing a different set of biases and a different set of coupling strengths during each of a plurality of iterations.
- the method may further include: generating samples by a quantum processor for a set of biases and a set of coupling strengths.
- a processor-based system to computationally efficiently producing sample sets may be summarized as including: at least one processor; at least one nontransitory processor-readable medium communicatively coupled to the at least one processor and which stores processor executable instructions which, when executed by the at least one processor, cause the at least one processor to: initialize a generator parameter ⁇ ; initialize a discriminator parameter ⁇ ; draw a noise sample z k from a noise prior distribution r(z); for each respective noise sample z k drawn from the noise prior distribution r(z), draw a generated sample x (m
- z); draw a target sample ⁇ circumflex over (x) ⁇ (k) from a target distribution h,J that was generated by a quantum processor for a set of biases h and a set of coupling strengths J, where k 1, . . . , K; adjust the generator parameter ⁇ ; adjust the discriminator parameter ⁇ ; and determine whether the adjusted generator parameter ⁇ and the adjusted discrimin
- the processor executable instructions cause the processor further to: receive the set of biases and the set of coupling strength values before drawing the noise sample z k from the noise prior distribution r(z).
- the processor executable instructions cause the processor further to: in response to a determination that at least one of the adjusted generator parameter ⁇ or the adjusted discriminator parameter ⁇ do not meet the respective optimization criteria, draw a new noise sample z k from the noise prior distribution r(z).
- the processor executable instructions cause the processor further to: in a first iteration, receive a set of biases and a set of coupling strength values before drawing the noise sample from the noise prior distribution r(z); in response to a determination that at least one of the adjusted generator parameter ⁇ or the adjusted discriminator parameter ⁇ do not meet the respective optimization criteria, in a second iteration: receive a new set of biases and a new set of coupling strength values before drawing a new noise sample in the second iteration; and draw the new noise sample z k from the noise prior distribution r(z) in the second iteration.
- the at least one processor may draw a noise sample z k from a uniform distribution or a Gaussian distribution.
- the at least one processor may draw a noise sample z k from a multi-dimensional distribution.
- z) is a generator function
- the processor executable instructions may cause the processor further to: generate a generated sample x for each noise sample z k drawn from noise prior distribution r(z) via the generator function g ⁇ (x
- the processor executable instructions may cause the processor further to: generate M generated samples x (m
- k) being a respective vector of qubit states defined on ⁇ 1,1 ⁇ n , where m 1, . . . , M.
- the at least one processor may determine if a divergence between the generative distribution and the target distribution is minimized. To determine whether the adjusted generator parameter and the adjusted discriminator parameter are optimized the at least one processor may determine if the generator parameter ⁇ is minimized and the discriminator parameter ⁇ is maximized. To determine whether the adjusted generator parameter and the adjusted discriminator parameter are optimized the at least one processor may determine if the generator and the discriminator have converged. To determine whether the adjusted generator parameter and the adjusted discriminator parameter are optimized the at least one processor may determine if a change in a step size of the generator parameter ⁇ is negligible.
- the at least one processor may determine if a change in a step size of the discriminator parameter ⁇ is negligible. To determine if a change in a step size of the discriminator parameter ⁇ is negligible the at least one processor may determine if discriminator parameter does not change appreciably compared a previous iteration.
- the processor executable instructions may cause the processor further to: condition at least one of the generator or the discriminator on additional information, such as multiple sets of biases and multiple sets of coupling strengths.
- the processor executable instructions may cause the processor further to: employ a different set of biases and a different set of coupling strengths during each of a plurality of iterations.
- the at least one processor may include at least one digital processor, the at least one digital processor which performs all of the aforesaid acts.
- the at least one processor may include at least one quantum processor, the at least one quantum processor which generates samples for a set of biases and a set of coupling strengths.
- FIG. 1 is a flowchart illustrating a method for training an example GAN using samples generated by a quantum processor for a set of biases and a set of coupling strengths, according to the present systems and methods.
- FIG. 2 is a flowchart illustrating a method for training an example GAN using samples generated by a quantum processor for multiple sets of biases and multiple sets of coupling strengths, according to the present systems and methods.
- FIG. 3 is a schematic diagram of a hybrid computing system including a digital computer communicatively coupled to an analog computer, in accordance with the present methods and systems.
- Samples can be drawn from a quantum processor for a set of biases h and a set of coupling strengths J that correlate to an energy function that defines an Ising model.
- generating samples from the quantum processor can be challenging and slow.
- the present systems and methods describe combining a quantum processor with machine learning methods to post-process and reproduce samples generated from the quantum processor.
- Reproduced samples that are similar or identical to original samples that are drawn from a quantum processor can be desirable because the reproduced samples can replace original samples or can be added to original samples drawn. Samples that includes the reproduced samples can be used in sampling or finding minimum-cost solutions to optimization problems.
- GANs Generative Adversarial Networks
- a GAN can include a generator and a discriminator, both of which can be multilayer perceptrons.
- the generator generates samples from a noise prior distribution that is defined on input noise variables, and the discriminator is trained to determine the probability of whether a sample is from the generator or from a target distribution.
- the discriminator can be considered an auxiliary neural network that is used to train the generator.
- JS divergence is part of a family of statistical divergences called f-divergences.
- f-divergences a family of statistical divergences.
- Nowozin et al shows that other divergences lead to more general variational divergence estimation approaches can be used to train a GAN.
- the f-divergence D f between a target distribution and a generative distribution in terms of pointwise probabilities (or densities) p(x), q(x), respectively, is defined by:
- D f ( , ) ⁇ sup [ T 99 ( x )] ⁇ [ ⁇ *( T ⁇ ( x ))]
- T ⁇ (x) is a is a discriminator that can comprise a multilayer perceptron parameterized by a discriminator parameter ⁇
- ⁇ * is a Fenchel dual (i.e., a convex conjugate) of a convex lower semi-continuous function ⁇
- generative distribution can comprise a multilayer perceptron parameterized by a generator parameter ⁇ .
- the generative model of the GAN can be estimated using variational divergence minimization.
- the GAN can be trained with the objective of maximizing the discriminator parameter ⁇ and minimizing the generator parameter ⁇ of a variational lower bound function V( , ⁇ , ⁇ ) expressed as:
- training a GAN by minimizing the generator parameter ⁇ and maximizing the discriminator parameter ⁇ can include, in separate acts, adjusting the generator parameter ⁇ , approximating the distance between a generative distribution and a target distribution by adjusting the discriminator parameter ⁇ , and then repeating the aforementioned acts.
- training a GAN can include simultaneously adjusting the generator parameter ⁇ and measuring the distance between a generative distribution and a target distribution by adjusting the discriminator parameter ⁇ .
- One approach for adjusting the generator parameter ⁇ and the discriminator parameter ⁇ is to use gradient optimization for back-propagation. Calculating a gradient to train the GAN requires differentiation so continuous distributions are typically used to train the generator and the discriminator of a GAN.
- An example of a target distribution that can be used for training a GAN is a sample distribution generated by a quantum processor.
- the quantum processor can comprise a number of qubits n that each have a bias applied to realize the h term of an Ising model and a pair of qubits is coupled with a coupling strength J.
- the quantum processor can produce samples according to methods described in U.S. Pat. No. 9,218,567, for example.
- FIG. 1 is a flowchart illustrating a method 100 for training an example GAN using samples generated by a quantum processor for a set of biases and a set of coupling strengths, according to the present systems and methods.
- the GAN includes a generator and a discriminator.
- Method 100 includes acts 102 - 120 , though in other implementations, certain acts can be omitted and/or additional acts can be added.
- Method 100 can be performed by, for example, a hybrid computing system including a digital computer and a quantum processor in response to instructions or a program submitted by a user.
- a generator parameter ⁇ and a discriminator parameter ⁇ are each initialized.
- the generator parameter ⁇ and the discriminator parameter ⁇ can each be initialized with a value selected by a user.
- a noise sample z k is drawn from a noise prior distribution r(z).
- the noise prior distribution can be a fixed distribution.
- the noise prior distribution can be a uniform distribution or a Gaussian distribution (i.e., z ⁇ [0,1] or z ⁇ (0,1)).
- the noise prior distribution can be any multi-dimensional distribution.
- z) is a generator (i.e., a probability mass function) that is used to generate a generated sample x for each noise sample z k drawn from noise prior distribution r(z). Generated samples x collectively constitute the generative distribution ⁇ .
- z) can generate generated samples x that belong to a different data space or set than noise samples z of the noise prior distribution r(z).
- the generated sample x is a vector of qubit states defined on ⁇ 1,1 ⁇ n where n is the number of qubits.
- z) may draw noise samples z from a noise prior distribution defined on [0,1] to generate generated samples x that are defined on ⁇ 1,1 ⁇ n .
- the pointwise probability q ⁇ (x) may be the probability of n qubits being in a set of states described in elements of the vector of qubit states (i.e., generated sample x).
- k) is drawn from the generator g ⁇ (x
- the generative distribution ⁇ can generate M generated samples x (m
- the generator parameter ⁇ and the discriminator parameter ⁇ are adjusted.
- the generator parameter ⁇ and the discriminator parameter ⁇ can be adjusted separately or simultaneously. Their adjustment acts are shown as 110 and 112 , respectively.
- the generator parameter ⁇ is adjusted.
- an importance weight estimator ⁇ tilde over (p) ⁇ (x) that can estimate the weight of the pointwise probability p(x) of the target distribution h,J generated by the quantum processor for a set of biases h and a set of coupling strengths J can be defined by:
- w(x) is an importance weight and ⁇ is a partition function.
- the partition function ⁇ normalizes the importance weight estimator ⁇ tilde over (p) ⁇ (x) but can be difficult to estimate.
- One approach to addressing this difficulty is to define a conditional partition function ⁇ (z) that is conditioned on a respective noise sample z.
- a conditional importance weight estimator can be defined as a conditional pointwise probability ⁇ tilde over (p) ⁇ (x
- conditional partition function ⁇ (z) is defined by:
- ⁇ ⁇ ( z ) E g ⁇ ( x
- z ) [ w ⁇ ( x ) ] ⁇ x ⁇ ⁇ - 1 , 1 ⁇ n g ⁇ ( x
- z) and the generator g ⁇ can be as expressed as:
- the importance weight w(x) may be normalized.
- the normalized importance weight is denoted by ⁇ tilde over (w) ⁇ (x (m) ) and can be a Monte-Carlo estimate of the normalized importance weights defined by:
- z) and the normalized importance weight ⁇ tilde over (w) ⁇ (x (m) ) are independent of the generator parameter ⁇ and the importance weight estimator ⁇ tilde over (p) ⁇ (x
- the second term in the expected conditional KL divergence can be estimated over the prior noise distribution r(z).
- the second term in the expected conditional KL divergence can be estimated as:
- Adjusting the generator parameter ⁇ can include using a gradient to calculate weight adjustments for back-propagation in the expected conditional KL divergence.
- the first term of the expected conditional KL divergence is independent of the generator parameter ⁇ (i.e., derivative is zero), therefore the gradient can be approximated by differentiating the second term of the expected conditional KL divergence.
- the gradient can be expressed as:
- Adjusting the generator parameter ⁇ can include using K noise samples z k from the noise prior distribution r(z) to further approximate the gradient ⁇ ⁇ r(z) [D KL ( ⁇ tilde over (p) ⁇ (x
- z))] of the expected conditional KL divergence for k 1, . . . , K.
- the gradient can be approximated as follows:
- the gradient can be updated with a respective step size ⁇ ⁇ for the generator parameter ⁇ .
- Adjusting the discriminator parameter ⁇ can include maximizing the discriminator parameter ⁇ associated with the discriminator ⁇ in the variational lower bound function V( h,J , ⁇ , ⁇ ).
- the target distribution h,J is generated by the quantum processor for a set of biases h and a set of coupling strengths J.
- Adjusting the discriminator parameter ⁇ can further include estimating a divergence between the generative distribution 74 and the target distribution using a variational lower bound function.
- V ( , ⁇ , ⁇ ) ( [ T ⁇ ( x )] ⁇ [ ⁇ *( T ⁇ ( x ))]
- Adjusting the discriminator parameter ⁇ can include using a gradient to calculate weight adjustments for back-propagation in the variational lower bound function. It can be beneficial to approximate the variational lower bound function to simplify calculating a gradient with respect to discriminator parameter ⁇ .
- the first term in the variational lower bound function denoted by [T ⁇ (x)] can be approximated by the target samples ⁇ circumflex over (x) ⁇ (k) drawn from the target distribution h,J generated by the quantum processor in act 108 . This may be expressed as:
- the second term in the variational lower bound function can be approximated using samples from noise prior distribution r(z) and generator g ⁇ (x
- the variational lower bound function can then be expressed as:
- adjusting the discriminator parameter ⁇ can include using a gradient to calculate weight adjustments for back-propagation in the variational lower bound function.
- the gradient of the variational lower bound function with respect to the discriminator parameter ⁇ can be expressed by:
- the gradient can be updated with a respective step size ⁇ ⁇ for the discriminator parameter ⁇ .
- method 100 ends at act 116 .
- the generator parameter ⁇ is minimized and the discriminator parameter ⁇ is maximized.
- the generator and the discriminator converge.
- the step size ⁇ ⁇ of the generator parameter and the step size ⁇ ⁇ of the discriminator parameter can each be measured in a certain metric (e.g., Euclidean distance p ).
- training can terminate when at least one of the respective step sizes ⁇ ⁇ , ⁇ ⁇ of the generator parameter ⁇ and the discriminator ⁇ , measured as a Euclidean distance, is less than a value ⁇ .
- examples of the value ⁇ can include: 0, 10 ⁇ 8 , 0.001, etc.). Selecting the value ⁇ can be depend on a number of iterations of acts 104 to 114 of method 100 .
- method 100 can terminate when samples from the generator g ⁇ can be considered reproduced samples of samples from the target distribution h,J generated by the quantum processor.
- act 104 is performed.
- An additional iteration of acts 104 - 114 is executed if termination criteria are not met. For example, if the divergence between the generative distribution and the target distribution is not minimized, act 104 is performed.
- the generator parameter ⁇ is not minimized and the discriminator parameter ⁇ is not maximized.
- at least one of the respective step sizes ⁇ y ⁇ , ⁇ y ⁇ of the generator parameter ⁇ and the discriminator parameter ⁇ is different from that of a previous iteration.
- the respective step sizes ⁇ ⁇ , ⁇ ⁇ of the generator parameter ⁇ and the discriminator ⁇ , when measured as a Euclidean distance, is more than a value ⁇ .
- examples of the value ⁇ can include: 0, 10 ⁇ 8 , 0.001, etc.).
- Directing the generator and/or the discriminator can be done by conditioning at least one of the models on additional information, such as multiple sets of biases and multiple sets of coupling strengths.
- each set of biases and each set of coupling strengths can be different from those of a preceding iteration.
- the multiple sets of biases and multiple sets of coupling strengths can be submitted as inputs to the generators and discriminators of the GAN, thereby being a part of the inputs.
- FIG. 2 a flowchart illustrating a method 200 for training an example GAN using samples generated by a quantum processor for multiple sets of biases and multiple sets of coupling strengths, according to the present systems and methods.
- the GAN includes a generator and a discriminator.
- Method 200 includes acts 202 - 240 , though in other implementations, certain acts can be omitted and/or additional acts can be added.
- Method 200 can be performed by, for example, a hybrid computing system including a digital computer and a quantum processor in response to instructions or a program submitted by a user.
- a generator parameter ⁇ and a discriminator parameter ⁇ are each initialized.
- the generator parameter ⁇ and the discriminator parameter ⁇ can each be initialized with a value selected by a user.
- act 202 may further include initializing a first set of biases and a first set of coupling strengths.
- a GAN may be initially trained on a first set of biases h and a first set of coupling strengths J.
- a first set of biases h and a first set of coupling strengths J values are received.
- the first set of biases h and the first set of coupling strengths J can be received from a user as inputs to the generator and the discriminator of the GAN.
- the first set of biases h and the first set of coupling strengths J can be received from a quantum processor as inputs to the generator and the discriminator of the GAN.
- each value for biases h can correlate to a respective local bias applied to a qubit at a state during evolution of the quantum processor.
- biases h and coupling strengths J may be updated in subsequent iterations of acts of method 200 as biases and coupling strengths on the quantum processor change slowly during an anneal. Such an approach may be useful in persistent training applications, for example.
- a noise sample z is drawn from a noise prior distribution r(z).
- the noise prior distribution can be a fixed distribution.
- the noise prior distribution can be a uniform distribution or a Gaussian distribution.
- the noise prior distribution can be any multi-dimensional distribution.
- the pointwise probability q ⁇ (x) of the generative distribution ⁇ is defined by: q ⁇ ( x
- h, J ) ⁇ z g ⁇ ( x
- z, h, J) can generate generated samples x that belong to a different data space or set than noise samples z of the noise prior distribution r(z).
- the generated sample x is a vector of qubit states defined on ⁇ 1,1 ⁇ n where n is the number of qubits.
- z, h, J) is further conditioned on a first set of biases h and a first set of coupling strengths J retrieved from the quantum processor in act 204 .
- sets of biases h and sets of coupling strengths J in subsequent iterations can have different values from the first set of biases h and the first set of coupling strengths J.
- the generator can be conditioned on either one of sets of biases h or sets of coupling strengths J.
- k) is drawn from the generator g ⁇ (x
- the generative distribution ⁇ can generate M generated samples x (m
- the generator parameter ⁇ and the discriminator parameter ⁇ are adjusted.
- the generator parameter ⁇ and the discriminator parameter ⁇ can be adjusted separately or simultaneously. Their adjustment acts are shown as 214 and 216 , respectively.
- the generator parameter ⁇ is adjusted.
- the expected conditional KL divergence can be minimized using aforementioned methods, such as method 100 of FIG. 1 , with the variation that the generator g ⁇ is conditioned on a noise sample z, the first set of biases h, and the first set of coupling strengths J.
- the generator g ⁇ is conditioned on a noise sample z and either a set of biases h or a set of coupling strengths J.
- the second term of the expected conditional KL divergence can be estimated as:
- Adjusting the generator parameter ⁇ can include using a gradient to calculate weight adjustments for back-propagation in the expected conditional KL divergence.
- the gradient can be expressed as:
- the gradient can be further approximated as:
- the gradient can be updated with a respective step size ⁇ ⁇ for the generator parameter ⁇ .
- the discriminator parameter ⁇ adjusted can include maximizing the discriminator parameter ⁇ associated with the discriminator ⁇ in the variational lower bound function V( , ⁇ , ⁇ ).
- the target distribution is generated by the quantum processor for the first set of biases h and the first set of coupling strengths J.
- the variational lower bound function can be approximated as:
- adjusting the discriminator parameter ⁇ can include using a gradient to calculate weight adjustments for back-propagation in the variational lower bound function.
- the gradient of the variational lower bound function with respect to the discriminator parameter ⁇ can be expressed by:
- the gradient can be updated with a respective step size ⁇ ⁇ for the discriminator parameter ⁇ .
- method 200 ends at act 220 .
- the generator parameter ⁇ is minimized and the discriminator parameter ⁇ is maximized.
- the generator and the discriminator converge.
- the step size ⁇ ⁇ of the generator parameter and the step size ⁇ ⁇ of the discriminator parameter can each be measured in a certain metric (e.g., Euclidean distance p ).
- training can terminate when at least one of the respective step sizes ⁇ ⁇ , ⁇ ⁇ of the generator parameter ⁇ and the discriminator ⁇ , measured as a Euclidean distance, is less than a value ⁇ .
- examples of the value ⁇ can include: 0, 10 ⁇ 8 , 0.001, etc.). Selecting the value ⁇ can be depend on a number of iterations of acts 204 to 218 of method 200 . In some cases, samples from the generator g ⁇ can be considered reproduced samples of samples from the target distribution generated by the quantum processor.
- act 204 is performed, wherein a second set of biases replaces the first set of biases, and a second set of coupling strengths replaces the first set of coupling strengths.
- the generator parameter ⁇ is not minimized and/or the discriminator parameter ⁇ is not maximized, the generator is conditioned on a noise sample, the second set of biases, and the second set of coupling strengths received from the quantum processor in act 204 .
- the second set of biases and the second set of coupling strengths has different values from the first set of biases and the second set of coupling strengths.
- an additional set of biases may replace the preceding set of biases and an additional set of coupling strengths may replace the preceding set of coupling strengths.
- the above described method(s), process(es), or technique(s) could be implemented by a series of processor readable instructions stored on one or more nontransitory processor-readable media. Some examples of the above described method(s), process(es), or technique(s) method are performed in part by a specialized device such as an adiabatic quantum computer or a quantum annealer or a system to program or otherwise control operation of an adiabatic quantum computer or a quantum annealer, for instance a computer that includes at least one digital processor.
- the above described method(s), process(es), or technique(s) may include various acts, though those of skill in the art will appreciate that in alternative examples certain acts may be omitted and/or additional acts may be added.
- FIG. 3 illustrates a hybrid computing system 300 including a digital computer 305 coupled to an analog computer 350 .
- the analog computer 350 is a quantum computer.
- the exemplary digital computer 305 includes a digital processor (CPU) 310 that may be used to perform classical digital processing tasks.
- CPU digital processor
- Digital computer 305 may include at least one digital processor (such as central processor unit 310 with one or more cores), at least one system memory 320 , and at least one system bus 317 that couples various system components, including system memory 320 to central processor unit 310 .
- the digital processor may be any logic processing unit, such as one or more central processing units (“CPUs”), graphics processing units (“GPUs”), digital signal processors (“DSPs”), application-specific integrated circuits (“ASICs”), programmable gate arrays (“FPGAs”), programmable logic controllers (PLCs), etc.
- CPUs central processing units
- GPUs graphics processing units
- DSPs digital signal processors
- ASICs application-specific integrated circuits
- FPGAs programmable gate arrays
- PLCs programmable logic controllers
- Digital computer 305 may include a user input/output subsystem 311 .
- the user input/output subsystem includes one or more user input/output components such as a display 312 , mouse 313 , and/or keyboard 314 .
- System bus 317 can employ any known bus structures or architectures, including a memory bus with a memory controller, a peripheral bus, and a local bus.
- System memory 320 may include non-volatile memory, such as read-only memory (“ROM”), static random-access memory (“SRAM”), Flash NANO; and volatile memory such as random access memory (“RAM”) (not shown).
- ROM read-only memory
- SRAM static random-access memory
- RAM random access memory
- Digital computer 305 may also include other non-transitory computer or processor-readable storage media or non-volatile memory 315 .
- Non-volatile memory 315 may take a variety of forms, including: a solid-state disk, a hard disk drive, an optical disk drive, and/or a magnetic disk drive.
- the optical disk can be a CD-ROM or DVD, while the magnetic disk can be a magnetic floppy disk or diskette.
- Non-volatile memory 315 may communicate with a digital processor via system bus 317 and may include appropriate interfaces or controllers 316 coupled to system bus 317 .
- Non-volatile memory 315 may serve as long-term storage for processor- or computer-readable instructions, data structures, or other data (sometimes called program modules) for digital computer 305 .
- digital computer 305 has been described as employing hard disks, optical disks and/or magnetic disks, those skilled in the relevant art will appreciate that other types of non-volatile computer-readable media may be employed, such magnetic cassettes, flash memory cards, Flash, ROMs, smart cards, etc.
- non-volatile computer-readable media such magnetic cassettes, flash memory cards, Flash, ROMs, smart cards, etc.
- volatile memory can be cached to non-volatile memory, or to a solid-state disk that employs integrated circuits to provide non-volatile memory.
- system memory 320 may store instruction for communicating with remote clients and scheduling use of resources including resources on the digital computer 305 and analog computer 350 .
- system memory 320 may store processor- or computer-readable calculation instructions to perform pre-processing, co-processing, and post-processing to analog computer 350 .
- System memory 320 may store a set of analog computer interface instructions to interact with the analog computer 350 .
- Analog computer 350 may include an analog processor, such as quantum processor 340 .
- the analog computer 350 can be provided in an isolated environment, for example, in an isolated environment that shields the internal elements of the quantum computer from heat, magnetic field, and other external noise (not shown).
Abstract
Description
where hi are local biases and Ji,j are coupling strengths. The spin variables can be interpreted as magnetic poles in a physical particle system and the optimal solution can be called a ground state.
H e=(1−s)H i +sH f
where Hi is the initial Hamiltonian, Hf is the final Hamiltonian, He is the evolution or instantaneous Hamiltonian, and s is an evolution coefficient which controls the rate of evolution. If the rate of evolution is slow enough that the system is always in the instantaneous ground state of the evolution Hamiltonian, then transitions at anti-crossings (i.e., when the gap size is smallest) are avoided. Other evolution schedules are possible including non-linear, parametric, and the like. Initial values for biases and coupling strengths may be loaded onto a quantum processor and a quantum annealing algorithm may be executed for a certain anneal time. Qubit states can be read to obtain a solution, and the quantum processor may be annealed multiple times to obtain a sample of multiple solutions. Further details on adiabatic quantum computing systems, methods, and apparatus are described in, for example, U.S. Pat. Nos. 7,135,701; and 7,418,283.
Machine Learning
q θ(x)=∫z g θ(x|z)·r(z)dz
q θ(x)=∫z g θ(x|z)·r(z)dz
D f(,)≥sup[T 99(x)]−[ƒ*(T ϕ(x))]
q θ(x)=∫z g θ(x|z)·r(z)dz
V(, θ, ϕ)=([T ϕ(x)]−[ƒ*(T ϕ(x))]
q θ(x|h, J)=∫z g θ(x|z, h, J)·r(z)dz
where gθ(x|z, h, J) is a generator that is used to generate a generated sample x for each noise sample zk drawn from noise prior distribution r(z), the first set of biases h, and the first set of coupling strengths J. Generated samples x collectively constitute the generative distribution 74 . The generator gθ(x|z, h, J) can generate generated samples x that belong to a different data space or set than noise samples z of the noise prior distribution r(z). In one implementation, the generated sample x is a vector of qubit states defined on {−1,1}n where n is the number of qubits.
Claims (20)
q θ(x)∫z =g θ(x|z)·r(z)dz
q θ(x)=∫z g θ(x|z)·r(z)dz
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US16/714,103 US11468293B2 (en) | 2018-12-14 | 2019-12-13 | Simulating and post-processing using a generative adversarial network |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201862780029P | 2018-12-14 | 2018-12-14 | |
US16/714,103 US11468293B2 (en) | 2018-12-14 | 2019-12-13 | Simulating and post-processing using a generative adversarial network |
Publications (2)
Publication Number | Publication Date |
---|---|
US20200193272A1 US20200193272A1 (en) | 2020-06-18 |
US11468293B2 true US11468293B2 (en) | 2022-10-11 |
Family
ID=71071064
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/714,103 Active 2041-01-01 US11468293B2 (en) | 2018-12-14 | 2019-12-13 | Simulating and post-processing using a generative adversarial network |
Country Status (1)
Country | Link |
---|---|
US (1) | US11468293B2 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20200311525A1 (en) * | 2019-04-01 | 2020-10-01 | International Business Machines Corporation | Bias correction in deep learning systems |
US20220060235A1 (en) * | 2020-08-18 | 2022-02-24 | Qualcomm Incorporated | Federated learning for client-specific neural network parameter generation for wireless communication |
US20220366288A1 (en) * | 2017-03-10 | 2022-11-17 | Rigetti & Co, Llc | Modular Control in a Quantum Computing System |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11636682B2 (en) * | 2020-11-05 | 2023-04-25 | International Business Machines Corporation | Embedding contextual information in an image to assist understanding |
CN112508179A (en) * | 2020-12-17 | 2021-03-16 | 上海依图网络科技有限公司 | Method, apparatus and medium for constructing network structure |
EP4281848A1 (en) * | 2021-06-11 | 2023-11-29 | Samsung Electronics Co., Ltd. | Methods and systems for generating one or more emoticons for one or more users |
CN114819163B (en) * | 2022-04-11 | 2023-08-08 | 本源量子计算科技(合肥)股份有限公司 | Training method and device for quantum generation countermeasure network, medium and electronic device |
Citations (109)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3470828A (en) | 1967-11-21 | 1969-10-07 | James R Powell Jr | Electromagnetic inductive suspension and stabilization system for a ground vehicle |
US20020010691A1 (en) | 2000-03-16 | 2002-01-24 | Chen Yuan Yan | Apparatus and method for fuzzy analysis of statistical evidence |
US20030030575A1 (en) | 2001-05-07 | 2003-02-13 | Harmonic Data Systems Ltd. | Lossless data compression |
US6671661B1 (en) | 1999-05-19 | 2003-12-30 | Microsoft Corporation | Bayesian principal component analysis |
US20050119829A1 (en) | 2003-11-28 | 2005-06-02 | Bishop Christopher M. | Robust bayesian mixture modeling |
US20060041421A1 (en) | 2004-08-17 | 2006-02-23 | Contentguard Holdings, Inc. | Method and system for processing grammar-based legality expressions |
US20060047477A1 (en) | 2004-08-31 | 2006-03-02 | Benjamin Bachrach | Automated system and method for tool mark analysis |
US20060074870A1 (en) | 2004-09-30 | 2006-04-06 | Microsoft Corporation | Query graphs |
US20060115145A1 (en) | 2004-11-30 | 2006-06-01 | Microsoft Corporation | Bayesian conditional random fields |
US7135701B2 (en) | 2004-03-29 | 2006-11-14 | D-Wave Systems Inc. | Adiabatic quantum computation with superconducting qubits |
US20070011629A1 (en) | 2005-07-11 | 2007-01-11 | International Business Machines Corporation | Adaptive application of SAT solving techniques |
US20070162406A1 (en) | 2006-01-12 | 2007-07-12 | Lanckriet Gert R | Adjusted sparse linear programming method for classifying multi-dimensional biological data |
US20080069438A1 (en) | 2006-09-19 | 2008-03-20 | Microsoft Corporation | Identifying Repeated-Structure Elements in Images |
US20080103996A1 (en) | 2006-10-31 | 2008-05-01 | George Forman | Retraining a machine-learning classifier using re-labeled training samples |
US20080132281A1 (en) | 2006-08-21 | 2008-06-05 | Byoung-Hoon Kim | Approach to a unified su-mimo/mu-mimo operation |
US20080176750A1 (en) | 2007-01-12 | 2008-07-24 | Geordie Rose | Systems, devices, and methods for interconnected processor topology |
US20080215850A1 (en) | 2006-12-05 | 2008-09-04 | Berkley Andrew J | Systems, methods and apparatus for local programming of quantum processor elements |
US20080313430A1 (en) | 2007-06-12 | 2008-12-18 | Bunyk Paul I | Method and system for increasing quantum computer processing speed using digital co-processor |
US7493252B1 (en) | 1999-07-07 | 2009-02-17 | International Business Machines Corporation | Method and system to analyze data |
US20090077001A1 (en) | 2006-11-02 | 2009-03-19 | William Macready | Integrating optimization directly into databases |
US7533068B2 (en) | 2004-12-23 | 2009-05-12 | D-Wave Systems, Inc. | Analog processor comprising quantum devices |
US20090121215A1 (en) | 2007-11-08 | 2009-05-14 | Vicky Choi | Systems, devices, and methods for analog processing |
CN101473346A (en) | 2006-04-12 | 2009-07-01 | 法国卓然 | Method and device for zooming Robust super-resolution video |
US20090171956A1 (en) | 2007-10-11 | 2009-07-02 | Rakesh Gupta | Text categorization with knowledge transfer from heterogeneous datasets |
WO2009120638A2 (en) | 2008-03-24 | 2009-10-01 | D-Wave Systems Inc. | Systems, devices, and methods for analog processing |
US20090254505A1 (en) | 2008-04-08 | 2009-10-08 | Microsoft Corporation | Reconfigurable hardware accelerator for boolean satisfiability solver |
US20090322871A1 (en) | 2008-06-26 | 2009-12-31 | Toyota Motor Engineering & Manufacturing North America, Inc. | Method and system of sparse code based object classification with sensor fusion |
US20100010657A1 (en) | 2008-07-10 | 2010-01-14 | Palo Alto Research Center Incorporated | Methods and systems for active diagnosis through logic-based planning |
CN101657827A (en) | 2007-04-19 | 2010-02-24 | D-波系统公司 | The system, method and the device that are used for automated graphics identification |
WO2010071997A1 (en) | 2008-12-27 | 2010-07-01 | Kibboko, Inc. | Method and system for hybrid text classification |
US20100185422A1 (en) | 2009-01-20 | 2010-07-22 | Chevron U,S,A., Inc. | Stochastic inversion of geophysical data for estimating earth model parameters |
US20100228694A1 (en) | 2009-03-09 | 2010-09-09 | Microsoft Corporation | Data Processing Using Restricted Boltzmann Machines |
US20100332423A1 (en) | 2009-06-24 | 2010-12-30 | Microsoft Corporation | Generalized active learning |
JP2011008631A (en) | 2009-06-26 | 2011-01-13 | Canon Inc | Image conversion method and device, and pattern identification method and device |
US20110022369A1 (en) | 2009-07-27 | 2011-01-27 | International Business Machines Corporation | Modeling States of an Entity |
US20110044524A1 (en) | 2008-04-28 | 2011-02-24 | Cornell University | Tool for accurate quantification in molecular mri |
US20110047201A1 (en) | 2005-07-11 | 2011-02-24 | Macready William G | Systems, methods and apparatus for factoring numbers |
CN102037475A (en) | 2008-05-20 | 2011-04-27 | D-波系统公司 | Systems, methods, and apparatus for calibrating, controlling, and operating a quantum processor |
US20110142335A1 (en) | 2009-12-11 | 2011-06-16 | Bernard Ghanem | Image Comparison System and Method |
US20110231462A1 (en) | 2009-06-17 | 2011-09-22 | D-Wave Systems Inc. | Systems and methods for solving computational problems |
US20110238378A1 (en) | 2007-12-12 | 2011-09-29 | Allen Edward H | Computer systems and methods for quantum verification and validation |
US20110295845A1 (en) | 2010-05-27 | 2011-12-01 | Microsoft Corporation | Semi-Supervised Page Importance Ranking |
CN102324047A (en) | 2011-09-05 | 2012-01-18 | 西安电子科技大学 | High spectrum image atural object recognition methods based on sparse nuclear coding SKR |
CN102364497A (en) | 2011-05-06 | 2012-02-29 | 北京师范大学 | Image semantic extraction method applied in electronic guidance system |
US20120084235A1 (en) | 2010-09-30 | 2012-04-05 | Massachusetts Institute Of Technology | Structured prediction model learning apparatus, method, program, and recording medium |
US20120124432A1 (en) | 2010-11-16 | 2012-05-17 | Pesetski Aaron A | System and method for phase error reduction in quantum systems |
US20120149581A1 (en) | 2006-12-20 | 2012-06-14 | Zhongshan Hospital, Fudan University | Process of constructing oxidation-reduction nanomedicine quantum dots room temperature quantum bit networks |
US8244650B2 (en) | 2007-06-12 | 2012-08-14 | D-Wave Systems Inc. | Systems, methods, and apparatus for recursive quantum computing algorithms |
US20120215821A1 (en) | 2006-06-20 | 2012-08-23 | D-Wave Systems Inc. | Systems, devices, and methods for solving computational problems |
CN102651073A (en) | 2012-04-07 | 2012-08-29 | 西安电子科技大学 | Sparse dynamic ensemble selection-based SAR (synthetic aperture radar) image terrain classification method |
US20120254586A1 (en) | 2008-06-10 | 2012-10-04 | D-Wave Systems Inc. | Quantum and digital processor hybrid systems and methods to solve problems |
CN102831402A (en) | 2012-08-09 | 2012-12-19 | 西北工业大学 | Sparse coding and visual saliency-based method for detecting airport through infrared remote sensing image |
KR20130010181A (en) | 2011-07-18 | 2013-01-28 | 한양대학교 산학협력단 | Filtering method for detecting orientation of edge from image and image recognition method using thereof |
US20130097103A1 (en) | 2011-10-14 | 2013-04-18 | International Business Machines Corporation | Techniques for Generating Balanced and Class-Independent Training Data From Unlabeled Data Set |
US20130236090A1 (en) | 2012-03-12 | 2013-09-12 | Fatih Porikli | Learning Dictionaries with Clustered Atoms |
US20130245429A1 (en) | 2012-02-28 | 2013-09-19 | Siemens Aktiengesellschaft | Robust multi-object tracking using sparse appearance representation and online sparse appearance dictionary update |
US20140025606A1 (en) | 2010-11-19 | 2014-01-23 | William G. Macready | Methods for solving computational problems using a quantum processor |
US20140040176A1 (en) | 2010-12-02 | 2014-02-06 | At&T Intellectual Property I, L.P. | Adaptive Pairwise Preferences in Recommenders |
US20140152849A1 (en) | 2012-12-05 | 2014-06-05 | Xerox Corporation | Video capture of multi-faceted documents |
US20140187427A1 (en) | 2011-07-06 | 2014-07-03 | D-Wave Systems Inc. | Quantum processor based systems and methods that minimize an objective function |
US20140201208A1 (en) | 2013-01-15 | 2014-07-17 | Corporation Symantec | Classifying Samples Using Clustering |
US20140214836A1 (en) | 2007-02-16 | 2014-07-31 | Bodymedia, Inc. | Systems and methods using an individuals predicted type and context for behavioral modification |
US20140214835A1 (en) | 2013-01-29 | 2014-07-31 | Richard Thomas Oehrle | System and method for automatically classifying documents |
CN104050509A (en) | 2013-03-14 | 2014-09-17 | 国际商业机器公司 | Frequency arrangement for surface code on superconducting lattice |
US20140297235A1 (en) | 2013-01-31 | 2014-10-02 | Betazi, Llc | Production analysis and/or forecasting methods, apparatus, and systems |
US8863044B1 (en) | 2013-09-06 | 2014-10-14 | International Business Machines Corporation | Layout assessment method and system |
US20150006443A1 (en) | 2013-06-28 | 2015-01-01 | D-Wave Systems Inc. | Systems and methods for quantum processing of data |
US20150161524A1 (en) | 2013-12-05 | 2015-06-11 | D-Wave Systems Inc. | Sampling from a set spins with clamping |
CN104766167A (en) | 2015-03-31 | 2015-07-08 | 浪潮集团有限公司 | Tax administration big data analysis method using restricted Boltzmann machine |
US20150242463A1 (en) | 2014-02-25 | 2015-08-27 | Tsung-Han Lin | Systems, apparatuses, and methods for deep learning of feature detectors with sparse coding |
US20150248586A1 (en) | 2014-03-03 | 2015-09-03 | Xerox Corporation | Self-learning object detectors for unlabeled videos using multi-task learning |
CN104919476A (en) | 2013-01-15 | 2015-09-16 | 阿尔卡特朗讯 | Syndrome of degraded quantum redundancy coded states |
US20150269124A1 (en) | 2013-12-05 | 2015-09-24 | D-Wave Systems Inc. | Sampling from a set of spins with clamping |
US20150317558A1 (en) | 2014-05-01 | 2015-11-05 | Lockheed Martin Corporation | Quantum-assisted training of neural networks |
WO2015193531A1 (en) | 2014-06-16 | 2015-12-23 | Nokia Technologies Oy | Data processing |
US20160019459A1 (en) | 2014-07-18 | 2016-01-21 | University Of Southern California | Noise-enhanced convolutional neural networks |
WO2016029172A1 (en) | 2014-08-22 | 2016-02-25 | D-Wave Systems Inc. | Systems and methods for problem solving, useful for example in quantum computing |
US20160078600A1 (en) | 2013-04-25 | 2016-03-17 | Thomson Licensing | Method and device for performing super-resolution on an input image |
US20160110657A1 (en) | 2014-10-14 | 2016-04-21 | Skytree, Inc. | Configurable Machine Learning Method Selection and Parameter Optimization System and Method |
WO2016089711A1 (en) | 2014-12-05 | 2016-06-09 | Microsoft Technology Licensing, Llc | Quantum deep learning |
US9378733B1 (en) | 2012-12-19 | 2016-06-28 | Google Inc. | Keyword detection without decoding |
US20160191627A1 (en) | 2012-11-28 | 2016-06-30 | Nvidia Corporation | Method and apparatus for execution of applications in a cloud system |
US20160307305A1 (en) | 2013-10-23 | 2016-10-20 | Rutgers, The State University Of New Jersey | Color standardization for digitized histological images |
CA2984773A1 (en) | 2015-06-11 | 2016-12-15 | Megan E. Foster | Tip-proof feeding bowl for house pets |
WO2016210018A1 (en) | 2015-06-26 | 2016-12-29 | Microsoft Technology Licensing, Llc | Underwater container cooling via integrated heat exchanger |
WO2017031357A1 (en) | 2015-08-19 | 2017-02-23 | D-Wave Systems Inc. | Systems and methods for machine learning using adiabatic quantum computers |
WO2017031356A1 (en) | 2015-08-19 | 2017-02-23 | D-Wave Systems Inc. | Discrete variational auto-encoder systems and methods for machine learning using adiabatic quantum computers |
CN106569601A (en) | 2016-10-28 | 2017-04-19 | 华南理工大学 | Virtual driving system control method based on P300 electroencephalogram |
US20170132509A1 (en) | 2015-11-06 | 2017-05-11 | Adobe Systems Incorporated | Item recommendations via deep collaborative filtering |
WO2017124299A1 (en) | 2016-01-19 | 2017-07-27 | 深圳大学 | Multi-target tracking method and tracking system based on sequential bayesian filtering |
WO2017132545A1 (en) | 2016-01-29 | 2017-08-03 | D-Wave Systems Inc. | Systems and methods for generative learning |
USD795416S1 (en) | 2015-02-27 | 2017-08-22 | 3M Innovative Properties Company | Respirator mask |
US20170255871A1 (en) | 2016-03-07 | 2017-09-07 | D-Wave Systems Inc. | Systems and methods for machine learning |
US20170300817A1 (en) | 2016-04-18 | 2017-10-19 | D-Wave Systems Inc. | Systems and methods for embedding problems into an analog processor |
US20170357274A1 (en) | 2016-06-13 | 2017-12-14 | International Business Machines Corporation | Garment optimization |
US20180018584A1 (en) | 2015-02-13 | 2018-01-18 | National Ict Australia Limited | Learning from distributed data |
US20180025291A1 (en) | 2016-07-20 | 2018-01-25 | Carnegie Mellon University | Data Processing System for Generating Data Structures |
US20180065749A1 (en) | 2016-09-08 | 2018-03-08 | Wal-Mart Stores, Inc. | Systems and methods for pollinating crops via unmanned vehicles |
US20180137422A1 (en) | 2015-06-04 | 2018-05-17 | Microsoft Technology Licensing, Llc | Fast low-memory methods for bayesian inference, gibbs sampling and deep learning |
US20180157923A1 (en) | 2010-06-07 | 2018-06-07 | Affectiva, Inc. | Vehicular cognitive data collection using multiple devices |
US20180165554A1 (en) | 2016-12-09 | 2018-06-14 | The Research Foundation For The State University Of New York | Semisupervised autoencoder for sentiment analysis |
US20180165601A1 (en) | 2016-12-08 | 2018-06-14 | Microsoft Technology Licensing, Llc | Tomography and generative data modeling via quantum boltzmann training |
US20190005402A1 (en) | 2015-12-30 | 2019-01-03 | Google Llc | Quantum statistic machine |
US20190018933A1 (en) | 2016-01-15 | 2019-01-17 | Preferred Networks, Inc. | Systems and methods for multimodal generative machine learning |
US10296846B2 (en) | 2015-11-24 | 2019-05-21 | Xerox Corporation | Adapted domain specific class means classifier |
US10318881B2 (en) | 2013-06-28 | 2019-06-11 | D-Wave Systems Inc. | Systems and methods for quantum processing of data |
US20190180147A1 (en) | 2016-06-30 | 2019-06-13 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for cell annotation with adaptive incremental learning |
US10339466B1 (en) | 2013-09-11 | 2019-07-02 | Google Llc | Probabilistic inference in machine learning using a quantum oracle |
US20200410384A1 (en) * | 2018-03-11 | 2020-12-31 | President And Fellows Of Harvard College | Hybrid quantum-classical generative models for learning data distributions |
-
2019
- 2019-12-13 US US16/714,103 patent/US11468293B2/en active Active
Patent Citations (123)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US3470828A (en) | 1967-11-21 | 1969-10-07 | James R Powell Jr | Electromagnetic inductive suspension and stabilization system for a ground vehicle |
US6671661B1 (en) | 1999-05-19 | 2003-12-30 | Microsoft Corporation | Bayesian principal component analysis |
US7493252B1 (en) | 1999-07-07 | 2009-02-17 | International Business Machines Corporation | Method and system to analyze data |
US20020010691A1 (en) | 2000-03-16 | 2002-01-24 | Chen Yuan Yan | Apparatus and method for fuzzy analysis of statistical evidence |
US20030030575A1 (en) | 2001-05-07 | 2003-02-13 | Harmonic Data Systems Ltd. | Lossless data compression |
US20050119829A1 (en) | 2003-11-28 | 2005-06-02 | Bishop Christopher M. | Robust bayesian mixture modeling |
US7135701B2 (en) | 2004-03-29 | 2006-11-14 | D-Wave Systems Inc. | Adiabatic quantum computation with superconducting qubits |
US7418283B2 (en) | 2004-03-29 | 2008-08-26 | D-Wave Systems Inc. | Adiabatic quantum computation with superconducting qubits |
US20060041421A1 (en) | 2004-08-17 | 2006-02-23 | Contentguard Holdings, Inc. | Method and system for processing grammar-based legality expressions |
US20060047477A1 (en) | 2004-08-31 | 2006-03-02 | Benjamin Bachrach | Automated system and method for tool mark analysis |
US20060074870A1 (en) | 2004-09-30 | 2006-04-06 | Microsoft Corporation | Query graphs |
US20060115145A1 (en) | 2004-11-30 | 2006-06-01 | Microsoft Corporation | Bayesian conditional random fields |
US8008942B2 (en) | 2004-12-23 | 2011-08-30 | D-Wave Systems Inc. | Analog processor comprising quantum devices |
US7533068B2 (en) | 2004-12-23 | 2009-05-12 | D-Wave Systems, Inc. | Analog processor comprising quantum devices |
US20070011629A1 (en) | 2005-07-11 | 2007-01-11 | International Business Machines Corporation | Adaptive application of SAT solving techniques |
US20110047201A1 (en) | 2005-07-11 | 2011-02-24 | Macready William G | Systems, methods and apparatus for factoring numbers |
US20070162406A1 (en) | 2006-01-12 | 2007-07-12 | Lanckriet Gert R | Adjusted sparse linear programming method for classifying multi-dimensional biological data |
US20090278981A1 (en) | 2006-04-12 | 2009-11-12 | Zoran (France) | Method and apparatus for robust super-resolution video scaling |
CN101473346A (en) | 2006-04-12 | 2009-07-01 | 法国卓然 | Method and device for zooming Robust super-resolution video |
US20120215821A1 (en) | 2006-06-20 | 2012-08-23 | D-Wave Systems Inc. | Systems, devices, and methods for solving computational problems |
US20080132281A1 (en) | 2006-08-21 | 2008-06-05 | Byoung-Hoon Kim | Approach to a unified su-mimo/mu-mimo operation |
US20080069438A1 (en) | 2006-09-19 | 2008-03-20 | Microsoft Corporation | Identifying Repeated-Structure Elements in Images |
US20080103996A1 (en) | 2006-10-31 | 2008-05-01 | George Forman | Retraining a machine-learning classifier using re-labeled training samples |
US20090077001A1 (en) | 2006-11-02 | 2009-03-19 | William Macready | Integrating optimization directly into databases |
US8035540B2 (en) | 2006-12-05 | 2011-10-11 | D-Wave Systems Inc. | Systems, methods and apparatus for local programming of quantum processor elements |
US7876248B2 (en) | 2006-12-05 | 2011-01-25 | D-Wave Systems Inc. | Systems, methods and apparatus for local programming of quantum processor elements |
US20080215850A1 (en) | 2006-12-05 | 2008-09-04 | Berkley Andrew J | Systems, methods and apparatus for local programming of quantum processor elements |
US20120149581A1 (en) | 2006-12-20 | 2012-06-14 | Zhongshan Hospital, Fudan University | Process of constructing oxidation-reduction nanomedicine quantum dots room temperature quantum bit networks |
US8195596B2 (en) | 2007-01-12 | 2012-06-05 | D-Wave Systems Inc. | Systems, devices, and methods for interconnected processor topology |
US20080176750A1 (en) | 2007-01-12 | 2008-07-24 | Geordie Rose | Systems, devices, and methods for interconnected processor topology |
US20140214836A1 (en) | 2007-02-16 | 2014-07-31 | Bodymedia, Inc. | Systems and methods using an individuals predicted type and context for behavioral modification |
CN101657827A (en) | 2007-04-19 | 2010-02-24 | D-波系统公司 | The system, method and the device that are used for automated graphics identification |
US8073808B2 (en) | 2007-04-19 | 2011-12-06 | D-Wave Systems Inc. | Systems, methods, and apparatus for automatic image recognition |
US8244650B2 (en) | 2007-06-12 | 2012-08-14 | D-Wave Systems Inc. | Systems, methods, and apparatus for recursive quantum computing algorithms |
US20080313430A1 (en) | 2007-06-12 | 2008-12-18 | Bunyk Paul I | Method and system for increasing quantum computer processing speed using digital co-processor |
US20090171956A1 (en) | 2007-10-11 | 2009-07-02 | Rakesh Gupta | Text categorization with knowledge transfer from heterogeneous datasets |
US20090121215A1 (en) | 2007-11-08 | 2009-05-14 | Vicky Choi | Systems, devices, and methods for analog processing |
US8190548B2 (en) | 2007-11-08 | 2012-05-29 | D-Wave Systems Inc. | Systems, devices, and methods for analog processing |
US20110238378A1 (en) | 2007-12-12 | 2011-09-29 | Allen Edward H | Computer systems and methods for quantum verification and validation |
WO2009120638A2 (en) | 2008-03-24 | 2009-10-01 | D-Wave Systems Inc. | Systems, devices, and methods for analog processing |
US20110022820A1 (en) | 2008-03-24 | 2011-01-27 | D-Wave Systems Inc. | Systems, devices, and methods for analog processing |
US8421053B2 (en) | 2008-03-24 | 2013-04-16 | D-Wave Systems Inc. | Oubit based systems, devices, and methods for analog processing |
US20090254505A1 (en) | 2008-04-08 | 2009-10-08 | Microsoft Corporation | Reconfigurable hardware accelerator for boolean satisfiability solver |
US20110044524A1 (en) | 2008-04-28 | 2011-02-24 | Cornell University | Tool for accurate quantification in molecular mri |
CN102037475A (en) | 2008-05-20 | 2011-04-27 | D-波系统公司 | Systems, methods, and apparatus for calibrating, controlling, and operating a quantum processor |
US20120254586A1 (en) | 2008-06-10 | 2012-10-04 | D-Wave Systems Inc. | Quantum and digital processor hybrid systems and methods to solve problems |
US20090322871A1 (en) | 2008-06-26 | 2009-12-31 | Toyota Motor Engineering & Manufacturing North America, Inc. | Method and system of sparse code based object classification with sensor fusion |
US20100010657A1 (en) | 2008-07-10 | 2010-01-14 | Palo Alto Research Center Incorporated | Methods and systems for active diagnosis through logic-based planning |
WO2010071997A1 (en) | 2008-12-27 | 2010-07-01 | Kibboko, Inc. | Method and system for hybrid text classification |
US20100185422A1 (en) | 2009-01-20 | 2010-07-22 | Chevron U,S,A., Inc. | Stochastic inversion of geophysical data for estimating earth model parameters |
US20100228694A1 (en) | 2009-03-09 | 2010-09-09 | Microsoft Corporation | Data Processing Using Restricted Boltzmann Machines |
US20110231462A1 (en) | 2009-06-17 | 2011-09-22 | D-Wave Systems Inc. | Systems and methods for solving computational problems |
US20100332423A1 (en) | 2009-06-24 | 2010-12-30 | Microsoft Corporation | Generalized active learning |
US8340439B2 (en) | 2009-06-26 | 2012-12-25 | Canon Kabushiki Kaisha | Image conversion method and apparatus, and pattern identification method and apparatus |
JP2011008631A (en) | 2009-06-26 | 2011-01-13 | Canon Inc | Image conversion method and device, and pattern identification method and device |
US20110022369A1 (en) | 2009-07-27 | 2011-01-27 | International Business Machines Corporation | Modeling States of an Entity |
US20110142335A1 (en) | 2009-12-11 | 2011-06-16 | Bernard Ghanem | Image Comparison System and Method |
US20110295845A1 (en) | 2010-05-27 | 2011-12-01 | Microsoft Corporation | Semi-Supervised Page Importance Ranking |
US20180157923A1 (en) | 2010-06-07 | 2018-06-07 | Affectiva, Inc. | Vehicular cognitive data collection using multiple devices |
US20120084235A1 (en) | 2010-09-30 | 2012-04-05 | Massachusetts Institute Of Technology | Structured prediction model learning apparatus, method, program, and recording medium |
US20120124432A1 (en) | 2010-11-16 | 2012-05-17 | Pesetski Aaron A | System and method for phase error reduction in quantum systems |
US20140025606A1 (en) | 2010-11-19 | 2014-01-23 | William G. Macready | Methods for solving computational problems using a quantum processor |
US20140040176A1 (en) | 2010-12-02 | 2014-02-06 | At&T Intellectual Property I, L.P. | Adaptive Pairwise Preferences in Recommenders |
CN102364497A (en) | 2011-05-06 | 2012-02-29 | 北京师范大学 | Image semantic extraction method applied in electronic guidance system |
US20140187427A1 (en) | 2011-07-06 | 2014-07-03 | D-Wave Systems Inc. | Quantum processor based systems and methods that minimize an objective function |
US20160042294A1 (en) | 2011-07-06 | 2016-02-11 | D-Wave Systems Inc. | Quantum processor based systems and methods that minimize an objective function |
KR20130010181A (en) | 2011-07-18 | 2013-01-28 | 한양대학교 산학협력단 | Filtering method for detecting orientation of edge from image and image recognition method using thereof |
CN102324047A (en) | 2011-09-05 | 2012-01-18 | 西安电子科技大学 | High spectrum image atural object recognition methods based on sparse nuclear coding SKR |
US20130097103A1 (en) | 2011-10-14 | 2013-04-18 | International Business Machines Corporation | Techniques for Generating Balanced and Class-Independent Training Data From Unlabeled Data Set |
US20130245429A1 (en) | 2012-02-28 | 2013-09-19 | Siemens Aktiengesellschaft | Robust multi-object tracking using sparse appearance representation and online sparse appearance dictionary update |
US20130236090A1 (en) | 2012-03-12 | 2013-09-12 | Fatih Porikli | Learning Dictionaries with Clustered Atoms |
CN102651073A (en) | 2012-04-07 | 2012-08-29 | 西安电子科技大学 | Sparse dynamic ensemble selection-based SAR (synthetic aperture radar) image terrain classification method |
CN102831402A (en) | 2012-08-09 | 2012-12-19 | 西北工业大学 | Sparse coding and visual saliency-based method for detecting airport through infrared remote sensing image |
US20160191627A1 (en) | 2012-11-28 | 2016-06-30 | Nvidia Corporation | Method and apparatus for execution of applications in a cloud system |
US20140152849A1 (en) | 2012-12-05 | 2014-06-05 | Xerox Corporation | Video capture of multi-faceted documents |
US9378733B1 (en) | 2012-12-19 | 2016-06-28 | Google Inc. | Keyword detection without decoding |
US20140201208A1 (en) | 2013-01-15 | 2014-07-17 | Corporation Symantec | Classifying Samples Using Clustering |
CN104919476A (en) | 2013-01-15 | 2015-09-16 | 阿尔卡特朗讯 | Syndrome of degraded quantum redundancy coded states |
US20140214835A1 (en) | 2013-01-29 | 2014-07-31 | Richard Thomas Oehrle | System and method for automatically classifying documents |
US20140297235A1 (en) | 2013-01-31 | 2014-10-02 | Betazi, Llc | Production analysis and/or forecasting methods, apparatus, and systems |
CN104050509A (en) | 2013-03-14 | 2014-09-17 | 国际商业机器公司 | Frequency arrangement for surface code on superconducting lattice |
US20160078600A1 (en) | 2013-04-25 | 2016-03-17 | Thomson Licensing | Method and device for performing super-resolution on an input image |
US20150006443A1 (en) | 2013-06-28 | 2015-01-01 | D-Wave Systems Inc. | Systems and methods for quantum processing of data |
US10318881B2 (en) | 2013-06-28 | 2019-06-11 | D-Wave Systems Inc. | Systems and methods for quantum processing of data |
US9727824B2 (en) | 2013-06-28 | 2017-08-08 | D-Wave Systems Inc. | Systems and methods for quantum processing of data |
US8863044B1 (en) | 2013-09-06 | 2014-10-14 | International Business Machines Corporation | Layout assessment method and system |
US10339466B1 (en) | 2013-09-11 | 2019-07-02 | Google Llc | Probabilistic inference in machine learning using a quantum oracle |
US20160307305A1 (en) | 2013-10-23 | 2016-10-20 | Rutgers, The State University Of New Jersey | Color standardization for digitized histological images |
US20150161524A1 (en) | 2013-12-05 | 2015-06-11 | D-Wave Systems Inc. | Sampling from a set spins with clamping |
US20150269124A1 (en) | 2013-12-05 | 2015-09-24 | D-Wave Systems Inc. | Sampling from a set of spins with clamping |
US20150242463A1 (en) | 2014-02-25 | 2015-08-27 | Tsung-Han Lin | Systems, apparatuses, and methods for deep learning of feature detectors with sparse coding |
US20150248586A1 (en) | 2014-03-03 | 2015-09-03 | Xerox Corporation | Self-learning object detectors for unlabeled videos using multi-task learning |
US20150317558A1 (en) | 2014-05-01 | 2015-11-05 | Lockheed Martin Corporation | Quantum-assisted training of neural networks |
WO2015193531A1 (en) | 2014-06-16 | 2015-12-23 | Nokia Technologies Oy | Data processing |
US20160019459A1 (en) | 2014-07-18 | 2016-01-21 | University Of Southern California | Noise-enhanced convolutional neural networks |
WO2016029172A1 (en) | 2014-08-22 | 2016-02-25 | D-Wave Systems Inc. | Systems and methods for problem solving, useful for example in quantum computing |
US20160110657A1 (en) | 2014-10-14 | 2016-04-21 | Skytree, Inc. | Configurable Machine Learning Method Selection and Parameter Optimization System and Method |
WO2016089711A1 (en) | 2014-12-05 | 2016-06-09 | Microsoft Technology Licensing, Llc | Quantum deep learning |
US20180018584A1 (en) | 2015-02-13 | 2018-01-18 | National Ict Australia Limited | Learning from distributed data |
USD795416S1 (en) | 2015-02-27 | 2017-08-22 | 3M Innovative Properties Company | Respirator mask |
CN104766167A (en) | 2015-03-31 | 2015-07-08 | 浪潮集团有限公司 | Tax administration big data analysis method using restricted Boltzmann machine |
US20180137422A1 (en) | 2015-06-04 | 2018-05-17 | Microsoft Technology Licensing, Llc | Fast low-memory methods for bayesian inference, gibbs sampling and deep learning |
CA2984773A1 (en) | 2015-06-11 | 2016-12-15 | Megan E. Foster | Tip-proof feeding bowl for house pets |
WO2016210018A1 (en) | 2015-06-26 | 2016-12-29 | Microsoft Technology Licensing, Llc | Underwater container cooling via integrated heat exchanger |
WO2017031357A1 (en) | 2015-08-19 | 2017-02-23 | D-Wave Systems Inc. | Systems and methods for machine learning using adiabatic quantum computers |
WO2017031356A1 (en) | 2015-08-19 | 2017-02-23 | D-Wave Systems Inc. | Discrete variational auto-encoder systems and methods for machine learning using adiabatic quantum computers |
US20170132509A1 (en) | 2015-11-06 | 2017-05-11 | Adobe Systems Incorporated | Item recommendations via deep collaborative filtering |
US10296846B2 (en) | 2015-11-24 | 2019-05-21 | Xerox Corporation | Adapted domain specific class means classifier |
US20190005402A1 (en) | 2015-12-30 | 2019-01-03 | Google Llc | Quantum statistic machine |
US20190018933A1 (en) | 2016-01-15 | 2019-01-17 | Preferred Networks, Inc. | Systems and methods for multimodal generative machine learning |
WO2017124299A1 (en) | 2016-01-19 | 2017-07-27 | 深圳大学 | Multi-target tracking method and tracking system based on sequential bayesian filtering |
WO2017132545A1 (en) | 2016-01-29 | 2017-08-03 | D-Wave Systems Inc. | Systems and methods for generative learning |
US20170255871A1 (en) | 2016-03-07 | 2017-09-07 | D-Wave Systems Inc. | Systems and methods for machine learning |
US10817796B2 (en) | 2016-03-07 | 2020-10-27 | D-Wave Systems Inc. | Systems and methods for machine learning |
US20170300817A1 (en) | 2016-04-18 | 2017-10-19 | D-Wave Systems Inc. | Systems and methods for embedding problems into an analog processor |
US20170357274A1 (en) | 2016-06-13 | 2017-12-14 | International Business Machines Corporation | Garment optimization |
US20190180147A1 (en) | 2016-06-30 | 2019-06-13 | Konica Minolta Laboratory U.S.A., Inc. | Method and system for cell annotation with adaptive incremental learning |
US20180025291A1 (en) | 2016-07-20 | 2018-01-25 | Carnegie Mellon University | Data Processing System for Generating Data Structures |
US20180065749A1 (en) | 2016-09-08 | 2018-03-08 | Wal-Mart Stores, Inc. | Systems and methods for pollinating crops via unmanned vehicles |
CN106569601A (en) | 2016-10-28 | 2017-04-19 | 华南理工大学 | Virtual driving system control method based on P300 electroencephalogram |
US20180165601A1 (en) | 2016-12-08 | 2018-06-14 | Microsoft Technology Licensing, Llc | Tomography and generative data modeling via quantum boltzmann training |
US20180165554A1 (en) | 2016-12-09 | 2018-06-14 | The Research Foundation For The State University Of New York | Semisupervised autoencoder for sentiment analysis |
US20200410384A1 (en) * | 2018-03-11 | 2020-12-31 | President And Fellows Of Harvard College | Hybrid quantum-classical generative models for learning data distributions |
Non-Patent Citations (255)
Title |
---|
"An implementation of the high-throughput computing system using the GPU (005)", no English translations, 2019-516164, IEICE Technical Report, vol. 114 No. 302, Nov. 13-14, 2014 , 12 pages. |
"Cluster Analysis", UIUC, 2013. |
"Neuro-computing for Parallel and Learning Information Systems", 2019-516164, www.jstage.jst.go.jp/article/sicej/1962/27/3/27_3_255/_article/-char/ja,Nov. 14, 2021, 17 pages. |
Achille et Soatto, "Information Dropout: Learning Optimal Representations Through Noise" Nov. 4, 2016, ICLR, arXiv:1611.01353v1, pp. 1-12. (Year: 2016). |
Adachi, S.H et al., "Application of Quantum Annealing to Training of Deep Neural Networks," URL:https://arxiv.org/ftp/arxiv/papers/151 0/1510.06356.pdf, Oct. 21, 2015, 18 pages. |
Amin , et al., "Quatum Boltzmann Machine". arXiv:1601.02036v1, Jan. 8, 2016. |
Amin, "Effect of Local Minima on Adiabatic Quantum Optimization," Physical Review Letters 100(130503), 2008, 4 pages. |
Anonymous , "A Robust Learning Approach to Domain Adaptive Object Detection". CVPR, 2019. |
Awasthi et al., "Efficient Learning of Linear Seperators under Bounded Noise" Mar. 12, 2015, arXiv: 1503.035S4v1, pp. 1-23. (Year: 2015). |
Awasthi et al., "Learning and 1-bit Compressed Sensing under Asymmetric Noise" Jun. 6, 2016, JMLR, pp. 1-41. (Year: 2016.) |
Azadi , et al., "Auxiliary Image Regulation for Deep CNNs with Noisy Labels". arXiv:1511.07069v2 (2016). |
B. Sallans and G.E. Hitton , "Reinforcement Learning with Factored States and Actions". JMLR, 5:1063-1088, 2004. |
Bach , et al., "Optimization with Sparsity-Inducing Penalties". arXiv:1108.0775v2, Nov. 22, 2011. |
Bach et al., "On the Equivalence between Herding and Conditional Gradient Algorithms," Proceedings of the 29th International Conference on Machine Learning, 2012, 8 pages. |
Bach, F. et al., "Optimization with Sparsity-Inducing Penalties," arXiv:1108.0775v2 [cs.LG], Nov. 22, 2011, 116 pages. |
Bahnsen , et al., "Feature Engineering Strategies for Credit Card Fraud Detection", Expert systems with applications Elsevier Jun. 1, 2016. https://www.sciencedirect.com/science/article/abs/pii/S0957417415008386?via%3Dihub. |
Barron-Romero, Carlos , "Classical and Quantum Algorithms for the Boolean Satisfiability Problem", CoRR, Abs/1510.02682 )Year:2015). |
Bearman , et al., "What's the Point: Semantic Segmentation with Point Supervision". ECCV, Jul. 23, 2016. https://arxiv.org/abs/1506.02106. |
Bell , et al., "The "Independent Components" of Natural Scenes are Edge Filters", Vision Res. 37(23) 1997,:pp. 3327-3338. |
Bellman, R. E., "Dynamic Programming". Princeton University Press, Princeton, NJ. Republished 2003: Dover, ISBN 0-486-42809-5. |
Benedetti et al., "Quantum-assisted learning of graphical models with arbitrary pairwise connectivity" Sep. 8, 2016, arXiv: 1609.02542v1, pp. 1-13. (Year: 2016). |
Berkley, A.J. et al., "Tunneling Spectroscopy Using a Probe Qubit," arXiv:1210.6310v2 [cond-mat.supr-con], Jan. 3, 2013, 5 pages. |
Bhattacharyya , et al., "Data mining for credit card fraud: A comparitive study", Decision Support Systems 2011. https://www.semanticscholar.org/paper/Data-mining-for-credit-card-fraud%3A-A-comparative-Bhattacharyya-Jha/9d26f0ba02ee5efe9b9c7bdcb5f528c8b8253cf7. |
Bian , et al., "The Ising Model: teaching an old problem new tricks", D-wave systems. 2 (year 2010), 32 pages. |
Bielza , et al., "Bayesian networks in neuroscience: a survey", Oct. 16, 2014, Frontiers in Computational Neuroscience, vol. 8, Article 131, p. 1-23 (Year: 2014). |
Blanchard et al., "Classification with Asymmetric Label Noise: Consistency and Maximal Denoising" Aug. 5, 2016, arXiv: 1303.1208v3, pp. 1-47. (Year: 2016). |
Bolton , et al., "Statistical fraud detection: A review", Statistical Science 17(3) Aug. 1, 2002. https://projecteuclid.org/journals/statistical-science/volume-17/issue-3/Statistical-Fraud-Detection-A-Review/10.1214/ss/1042727940.full. |
Bornschein et al., "Bidirectional Helmholtz Machines" May 25, 2016, arXiv: 1506.03877v5. (Year: 2016). |
Brakel, P., Dieleman, S., & Schrauwen. "Training restricted Boltzmann machines with multi-tempering: Harnessing parallelization", 2012. |
Burda , et al., "Importance Weighted Autoencoders", arXiv:1509.00519 Nov. 7, 2016. https://arxiv.org/abs/1509.00519. |
Buss , "Introduction to Inverse Kinematics with Jacobian Transpose, Pseudoinverse and Damped Least Squares methods", Mathematics UCS 2004. https://www.math.ucsd.edu/˜sbuss/ResearchWeb/ikmethods/iksurvey.pdf. |
Chen , et al., "Domain Adaptive Faster R-CNN for Object Detection in the Wild", IEEE Xplore, 2018, https://arxiv.org/abs/1803.03243. |
Chen , et al., "Stochastic Gradient Hamiltonian Monte Carlo", arXiv:1402.4102 May 12, 2014. https://arxiv.org/abs/1402.4102. |
Chen et al., "Herding as a Learning System with Edge-of-Chaos Dynamics," arXiv:1602.030142V2 [stat.ML], Mar. 1, 2016, 48 pages. |
Chen et al., "Parametric Herding," Proceedings of the 13th International Conference on Artificial Intelligence and Statistics (AISTATS), 2010, pp. 97-104. |
Chinese Office Action for Application No. CN 2016800606343, dated May 8, 2021, 21 pages (with English translation). |
Cho, K-H., Raiko, T, & Ilin, A. , "Parallel tempering is efficient for learning restricted Boltzmann machines", 2010. |
Cho, Kyunghyun , et al., "On the Properties of Neural Machine Translation: Encoder-Decoder Approaches", arXiv:1409.1259v2, [cs.CL] Oct. 7, 2014, 9 pages. |
Courbariaux, M. , et al., "Binarized Neural Networks: Training Neural Networks with Weights and Activations Constrained to +1 or −1". http://arxiv.org/pdf/1602.02830.pdf. |
Courville, A. et al., "A Spike and Slab Restricted Boltzmann Machine," Proceedings of the 14th International Conference on Artificial Intelligence and Statistics (AISTATS), 2011, 9 pages. |
Dai , et al., "Generative Modeling of Convolutional Neural Networks". ICLR 2015. |
Deng, J. et al., "ImageNet: A Large-Scale Hierarchical Image Database," Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2009, 8 pages. |
Desjardins, G., Courville, A., Bengio, Y., Vincent, P., & Delalleau, O. "Parallel tempering for training of restricted Boltzmann machines", 2010. |
Doersch , "Tutorial on variational autoencoders", arXiv:1606.05908 Jan. 3, 2021. https://arxiv.org/abs/1606.05908. |
Dumoulin, V. et al., "On the Challenges of Physical Implementations of RBMs," Proceedings of the 28th AAAI Conference on Artificial Intelligence, vol. 2, Jul. 27, 2014, 7 pages. |
Dumoulin, Vincent , et al., "On the Challenges of Physical Implementations of RBMs", https://arxiv.org/abs/1312.5258v2, Oct. 24, 2014. |
Dumoulin, Vincent, et al. "On the Challenges of Physical implementations of RBMs". arXiv:1312.5258v1, Dec. 13, 2013. |
Elkan, C., "Learning Classifiers from Only Positive and Unlabeled Data," KDD08: The 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Las Vegas Nevada USA Aug. 24-27, 2008, 8 pages. |
Extended European Search Report for EP Application No. 16837862.8, dated Apr. 3, 2019, 12 pages. |
Fabius, Otto , et al., "Variational Recurrent Auto-Encoders", Accepted as workshop contributions at ICLR 2015, 5 pages. |
Fergus, R. et al., "Semi-Supervised Learning in Gigantic Image Collections," Advances in Neural Information Processing Systems, vol. 22, 2009, 8 pages. |
First Office Action dated Nov. 29, 2021 in CN App No. 2016800731803. (English Translation). |
First Office Action issued in Chinese No. 2018101287473 with English translation, dated Jul. 12, 2021, 16 pages. |
Freidman, et al., "Learning Bayesian Networks from Data", Internet Movie Database, http://www.imdb.com, 19 pages. |
Freund, Y. et al., "Large Margin Classification Using the Perceptron Algorithm," Machine Learning 37(3), 1999, 19 pages. |
Friedman , et al., "Learning Bayesan Networks from Data", Stanford Robotics, http://robotics.stanford.edu/people/nir/tutorial/index.html. |
Fung, G. et al., "Parameter Free Bursty Events Detection in Text Streams," Proceedings of the 31st VLDB Conference, Trondheim, Norway, 2005, 12 pages. |
G. Hinton, N. Srivastava, et. al , "Improving neural networks by preventing co-adaptation of feature detectors". CoRR , abs/1207.0580, 2012. |
G.A. Rummery and M. Niranjan , "Online Q-Learning using Connectionist Systems". CUED/FINFENG/TR 166, Cambridge, UK, 1994. |
Gal , et al., "Bayesian Convolutional Neural Networks With Bernoulli Approximate Variational Inference". arXiv:1506.02158v6, 2016. |
Geordie, "First Ever DBM Trained Using a Quantum Computer," URL:https://dwave.wordpress.com/2014/01/06 /first-ever-dbm-trained-using-a-quantum-computer/, Jan. 6, 2014, 8 pages. |
Geordie, "Training DBMs with Physical neural nets" In Hack The Multiverse, Jan. 24, 2014, pp. 2-5. |
Glynn , "Likelihood ratio gradient estimation for stochastic systems". Communications of the ACM, 1990. https://dl.acm.org/doi/10.1145/84537.84552. |
Gomez-Bombarelli , et al., "Automatic chemical designs using a data-driven continuous representation of molecules", arXiv:1610.02415 Dec. 5, 2017. https://arxiv.org/abs/1610.02415. |
Gómez-Bombarelli et al., "Automatic Chemical Design Using a Data-Driven Continuous Representation of Molecules," arXiv:1610.02415v3: Dec. 2017. (26 pages). |
Goodfellow, Ian J., et al., "Generative Adversarial Nets", arXiv:1406.2661v1 [stat.ML], 9 pages., Jun. 10, 2014. |
Grassberger, "Entropy Estimates from Insufficient Samplings," arXiv:physics/0307138v2 [physics.data-an], Jan. 4, 2008, 5 pages. |
Grathwohl , et al., "Backpropagation through the void: Optimizing control variates for biack-box gradient etimation". arXiv:1711.00123, Feb. 23, 2018. https://arxiv.org/abs/1711.00123. |
Gregor , et al., "Deep autoregressive networks". arXiv:1310.8499, May 20, 2014. https://arxiv.org/abs/1310.8499. |
Gregor, Karol , et al., "Draw: A Recurrent Neural Network For Image Generation", Proceedings of the 32nd International Conference on Machine Leaning, Lille, France, 2015, JMLR: W&CP vol. 37. Copyright 2015, 10 pages. |
Gu , et al., "Muprop: Unbiased backpropagation for stochastic neural networks", arXiv:1511.05176, Feb. 25, 2016. https://aixiv.org/abs/1511.05176. |
Hamze , "Sampling From a Set Spins With Clamping". U.S. Appl. No. 61/912,385, filed Dec. 5, 2013, 35 pages. |
Hees , "Setting up a Linked Data mirror from RDF dumps". Jörn's Blog, Aug. 26, 2015. SciPy Hierarchical Clustering and Dendrogram Tutorial | Jörn's Blog (joernhees.de). |
Heess, N. , et al., "Actor-Critic Reinforcement Learning with Energy-based Policies". JMLR, 24:43-57, 2012. |
Heidrich-Meisner , et al., "Reinforcement Learning in a Nutshell". http://image.diku.dk/igel/paper/RLiaN.pdf. |
Hidasi , et al., "Session-based recommendations with recurrent neural networks", ICRL Mar. 29, 2016. https://arxiv.org/abs/1511.06939. |
Hinton , "A practical Guide to Training Restricted Bolzmann Machines". Department of Computer Science university of Toronto, Aug. 2, 2010. |
Hinton et al., "A Practical Guide to Training Restricted Boltzmann Machines," Springer, pp. 599-619, Jan. 1, 2012. |
Hinton, Geoffrey , "A Practical Guide to Training Restricted Boltzmann Machines", Version 1, Department of Computer Science University of Toronto, Aug. 2, 2010, 21 pages. |
Hinton, Geoffrey E, et al., "Autoencoders, Minimum Description Length and Helmholtz Free Energy", Department of Computer Science, University of Toronto, Computation Neuroscience Laboratory, The Salk Institute, Mar. 1, 2001, 9 pages. |
Hinton, Geoffrey E, et al., "Reducing the Dimensionality of Data with Neural Networks", Science, wwwsciencemag.org, vol. 313, Jul. 28, 2006, pp. 504-507. |
Hinton, Geoffrey E. . Training products of experts by minimizing contrastive divergence. Neural Computation, 14:1771-1800, 2002. |
Hinton, Geoffrey, Simon Osindero, and Yee-Whye Teh. A fast learning algorithm for deep belief nets. Neural computation, 18(7):1527-1554, 2006. |
Hischer, A. & Igel, C. , "A bound for the convergence rate of parallel tempering for sampling restricted Boltzmann machines", 2015. |
Hjelm, R. Devon, et al., "Boundary-Seeking Generative Adversarial Networks", arXiv:1702.08431v4 [stat.ML], 17 pages., Feb. 21, 2018. |
Humphrys, M. , http://computing.dcu.ie/ humphrys/PhD/ch2.html. |
Hurley, Barry , et al., "Proteus: A hierarchical Portfolio of Solvers and Transformations", arXiv:1306.5606v2 [cs. AI], Feb. 17, 2014, 17 pages. |
Husmeier , "Introduction to Learning Bayesian Networks from Data", Probabilistic Modeling in Bioinformatics and Medical Informatics 2005. https://link.springer.com/chapter/10.1007/1-84628-119-9_2. |
International Search Report and Written Opinion for PCT/US2018/065286, dated Apr. 16, 2019, 11 pages. |
International Search Report and Written Opinion for PCT/US2019/017124, dated May 30, 2019, 28 pages. |
International Search Report and Written Opinion of the International Searching Authority, dated Jan. 4, 2018, for International Application No. PCT/US2017/053303, 16 pages. |
International Search Report and Written Opinion, dated Oct. 13, 2014, for international Application No. PCT/US2014/044421, 13 pages. |
International Search Report, dated May 10, 2017, for International Application No. PCT/US2017/015401, 3 pages. |
International Search Report, dated Nov. 18, 2016, for International Application No. PCT/US2016/047627, 3 pages. |
Jaakkola et al., "Improving the Mean Field Approximation Via the Use of Mixture Distributions," 1998, 11 pages. |
Jain et al., "Estimating the class prior and posterior from noisy positives and unlabeled data" Jun. 28, 2016, arXiv: 1606.08561v1, pp. 1-19. (Year: 2016). |
Jang , et al., "Categorical reparameterization with Gumbel-Softmax", arXiv:1611.01144 Aug. 5, 2017. https://arxiv.org/abs/1611.01144. |
Japanese Office Action for Application No. JP 2019516164, dated Nov. 24, 2021, 33 pages (including English translation). |
Jenatton, R. et al., "Proximal Methods for Hierarchical Sparse Coding," arXiv:1009.2139v4 [stat.ML], Jul. 5, 2011, 38 pages. |
Jiang , et al., "Learning a discriminative dictionary for sparse coding via label consistent K-SVD", In CVPR 2011 (pp. 1697-1704) IEEE. Jun. 2011). |
Jordan, Michael I., Zoubin Ghahramani, Tommi S Jaakkola, and Lawrence K Saul. An introduction to variational methods for graphical models. Machine learning, 37(2):183-233, 1999. |
Katzgraber et al., "Glassy Chimeras Could Be Blind to Quantum Speedup: Designing Better Benchmarks for Quantum Annealing Machines," Physical Review X(4):021008, 2014. (8 pages). |
Ke et al., "Variational Convolutional Networks for Human-Centric Annotations" Nov. 20, 2016, pp. 120-135. (Year: 2016). |
Khalek, S. et al., "Automated SQL Query Generation for Systematic Testing of Database Engines," ASE '10 Proceedings of the IEEE/ACM international conference on Automated software engineering, 2010, 4 pages. |
Khalek, Shadi A, et al., "Automated SQL Query Generation for Systematic Testing of Database Engines", In proceedings of the IEEE/ACM International Conference of Automated Software Engineering pp. 329-332. Association of Computing Machinery. (Year: 2008). |
Kingma , et al., "Adam: A method for stochastic optimization", arXiv:1412.6980 Jan. 30, 2017. https://arxiv.org/abs/1412.6980. |
Kingma , et al., "Auto-encoding variational bayes". arXiv:1312.5258v1, May 1, 2014. https://arxiv.org/abs/1312.6114. |
Kingma, Diederik P, et al., "Semi-Supervised Learning with Deep Generative Models", arXiv:1406.5298v2 [cs.LG], Oct. 31, 2014, 9 pages. |
Kingma, Diedrik , et al., "Auto-Encoding Variational Bayes", https://arxiv.org/abs/1312.6114v10, May 1, 2014. |
Korean Office Action for Application 10-2019-7012141, dated Nov. 29, 2021, 18 pages (including English translation). |
Korenkevych , et al., "Benchmarking quantum hardware for training of fully visible boltzmann machines", arXiv:1611.04528 Nov. 14, 2016. https://arxiv.org/abs/1611.04528. |
Korenkevych et al., "Benchmarking Quantum Hardware for Training of Fully Visible Boltzmann Machines" Nov. 14, 2016, arXiv: 1611.04528v1, pp. 1-22. (Year: 2016). |
Krähenbühl, P. et al., "Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials," arXiv:1210.5644 [cs.CV], 2012, 9 pages. |
Krause , et al., "The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognition", 2016, Springer International Publishing AG, ECCV 2016, Part III, LNCS 9907, pp. 301-320 (Year:2016). |
Ku{hacek over (z)}elka, O. et al., "Fast Estimation of First-Order Clause Coverage through Randomization and Maximum Likelihood," ICML '08: Proceedings of the 25th international conference on Machine learning, 2008, 8 pages. |
Kuzelka, Ondrej , et al., "Fast Estimation of First-Order Clause Coverage through Randomization and Maximum Likelihood", In proceeding of the 25th International Conference on Machine Learning (pp. 504-5112). Association for Computing Machinery (Year:2008). |
L.Wan, M. Zieler, et. al. , "Regularization of Neural Networks using DropConnect". ICML, 2013. |
Lafferty, J. et al., "Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data," Proceedings of the 18th International Conference on Machine Learning 2001,10 pages. |
Le Roux, Nicolas , et al., "Representational Power of Restricted Boltzmann Machines and Deep Belief Networks", Dept. IRO, University of Montréal Canada, Technical Report 1294, Apr. 18, 2007, 14 pages. |
Le, Quoc , Marc'Aurelio Ranzato, Rajat Monga, Matthieu Devin, Greg Corrado, Kai Chen, Jeff Dean, and Andrew Ng. Building high-level features using large scale unsupervised learning. In ICML'2012, 2012. |
LeCun, Y., L. Bottou, Y. Bengio, and P. Haffner. Gradient based learning applied to document recognition. Proc. IEEE, 1998. |
Lee , et al., "Efficient sparse coding algorithm", NIPS, 2007,pp. 801-808. |
Lee, H. , et al., "Sparse deep belief net model for visual area v2". Advances in Neural Information Processing Systems, 20 . MIT Press, 2008. |
Li , et al., "R/'enyi Divergence Variational Inference", arXiv:1602.02311 Oct. 28, 2016. https://arxiv.org/abs/1602.02311. |
Li, X., et al., "Collaborative Variational Autoencoder for Recommender Systems," Published in KDD, Halifax, NS, Canada, Aug. 13-17, 2017, pp. 305-314. |
Lin , et al., "Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation". arXiv:1504.01013v4, 2016. |
Liu et Tao, "Classification with Noisy Labels by Importance Reweighting" Mar. 2016, pp. 447-461. (Year: 2016). |
Long, Philip M and Rocco Servedio. Restricted boltzmann machines are hard to approximately evaluate or simulate. In Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 703-710, 2010. |
Lovasz , et al., "A Correction: orthogonal representations and connectivity of graphs", Linear Algebra and it's Applications 313:2000 pp. 101-105. |
Lovasz , et al., "Orthogonal Representations and Connectivity of Graphs", Linear Algebra and its applications 114/115; 1989, pp. 439-454. |
Macready , et al., "Applications of Hardware Boltzmann Fits". U.S. Appl. No. 61/505,044, filed Jul. 6, 2011. |
Macready , et al., "Applications of Hardware Boltzmann Fits". U.S. Appl. No. 61/515,742, filed Aug. 5, 2011 , 11 pages. |
Macready , et al., "Applications of Hardware Boltzmann Fits". U.S. Appl. No. 61/540,208, filed Sep. 28, 2011 , 12 pages. |
Macready , et al., "Systems and Methods for Minimizing an Objective Function". U.S. Appl. No. 61/550,275, filed Oct. 21, 2011 , 26 pages. |
Macready, et al., "Systems and Methods for Minimizing an Objective Function". U.S. Appl. No. 61/557,783, filed Nov. 9, 2011 , 45 pages. |
Maddison , et al., "The concrete distribution: A continuous relaxation of discrete random variables", arXiv:1611.00712 Mar. 5, 2017. https://arxiv.org/abs/1611.00712. |
Makhzani, Alireza , et al., "Adversarial Autoencoders", arXiv:1511.05644v2 [cs.LG], May 25, 2016, 16 pages. |
Mandt , et al., "A Variational Analysis of Stochastic Gradient Algorithms", arXiv:1602.02666 Feb. 8, 2016. https://arxiv.org/abs/1602.02666. |
Menon et al., "Learning from Binary Labels with Instance-Dependent Corruption" May 4, 2016, pp. 1-41. (Year: 2016). |
Minh, V. et al., "Learning to Label Aerial Images from Noisy Data," Proceedings of the 29th International Conference on Machine Learning, Edinburgh, Scotland, 2012, 8 pages. |
Mirza Mehdi, et al., "Conditional Generative Adversarial Nets", arXiv:1411.1784v1 [cs.LG], 7 pages., Nov. 6, 2014. |
Misra , et al., "Seeing through the Human Reporting Bias: Visual Classifiers from Noisy Human-Centric Labels", 2016 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, 2016, pp. 2930-2939. |
Misra , et al., "Visual classifiers from noisy humancentric labels", in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. |
Miyata et al., "Consideration of 2D-FFT by Decomposition-of-Large Scale Data on Multi-GPU", IEICE Technical Report, vol. 114 No. 155, Computer Systems Jul. 28-30, 2014, Abstract, 12 pages. |
Mnih , et al., "Neural variational inference and learning in belief networks". arXiv:1402.0030 Jun. 4, 2016, https://arxiv.org/abs/1402.0030. |
Mnih , et al., "Variational inference for Monte Carlo objectives". arXiv:1602.06725, Jun. 1, 2016. https://arxiv.org/abs/1602.06725. |
Mnih, Andriy , et al., "Variational Inference for Mote Carlo Objectives", Proceedings of the 33rd International Conference on Machine Learning, New York, NY USA, 2016, JMLR: W&CP vol. 48, 9 pages. |
Mocanu et al., "A topological insight into restricted Boltzmann machines," Pre-print version: arXiv:1604.05978v2: Jul. 2016. (25 pages). |
Molchanov, Dmitry , et al., "Variational Dropout Sparsities Deep Neural Networks", https://arxiv.org/pdf/1701.05369v1.pdf, Jan. 19, 2017. |
Murphy , "A Brief Introduction to Graphical Models and Bayesian Networks", Oct. 14, 2001. https://www.cs.ubc.ca/˜murphyk/Bayes/bayes_tutorial.pdf. |
Murphy , "Machine Learning: a probaiistic perspective", MIT Press, 2012. http://noiselab.ucsd.edu/ECE228/Murphy_Machine_Learning.pdf. |
Murray, I. et al., "Bayesian Learning in Undirected Graphical Models: Approximate MCMC Algorithms," UAI '04: Proceedings of the 20th conference on Uncertainty in Artificial Intelligence, 2004, 8 pages. |
Muthukrishnan , et al., "Classical and quantum logic gates: an introduction to quantum computing", Quantum information seminar, )Year: 1999) 22 pages. |
N. Srivastava, G. Hinton, et. al , "Dropout: A Simple Way to Prevent Neural Networks from Overtting". ICML 15 (Jun):19291958, 2014. |
Natarajan, N. et al., "Learning with Noisy Labels," Advances in Neural Information Processing Systems 26, 2013, 9 pages. |
Neal , et al., "Memo Using Hamiltonian Dynamics", Handbook of Markov Chairs Monte Carlo 2011. |
Neven , et al., "Training a binary classifier with the quantum adiabatic algorithm", arXiv preprint arXivc:0811.0416, 2008, 11 pages. |
Neven, H. et al., "QBoost: Large Scale Classifier Training with Adiabatic Quantum Optimization," JMLR: Workshop and Conference Proceedings 25, 2012, 16 pages. |
Niv, "Reinforcement Learning in the Brain". Journal of Mathematical Psychology, 2009—Elsevier. |
Non-Final Office Action issued in U.S. Appl. No. 15/822,884 dated Feb. 17, 2022, 45 pages. |
Non-Final Office Action Issued in U.S. Appl. No. 16/336,625 dated Feb. 14, 2022, 22 pages. |
Nowozin, Sebastian , et al., "f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization", arXiv:1606.00709v1 [stat ML], 17 pages., Jun. 2, 2016. |
Olshausen, Bruno A, et al., "Emergence of simple cell receptive field properties by learning a sparse code for natural images", Nature, vol. 381, Jun. 13, 1996, pp. 607-609. |
Omidshafiei et al., "Hierarchical Bayesian Noise Inference for Robust Real-time Probabilistic Object Classification" Jul. 14, 2016, arXiv: 1605.01042v2, pp. 1-9. (Year: 2016). |
Ororbia et al., "Online Semi-Supervised Learning with Deep Hybrid Boltzmann Machines and Denoising Autoencoders" Jan. 18, 2016, ICLR, arXiv: 1511.06964v7, pp. 1-17. (Year: 2016). |
Paninski, "Estimation of Entropy and Mutual Information," Neural Computation 15:1191-1253, 2003. |
Patrini, et al., Making Neural Networks robust to label noise: a loss correction approach. arXiv: 1609.03683 (2016). |
Phua , et al., "A comprehensive survey", arXiv:1009.6119 Aug. 30, 2010. https://arxiv.0rg/abs/1009.6119. |
Pozzolo , et al., "Learned Lessons in credit card fraud detection from a practitioner perspective", Feb. 18, 2014. https://www.semanticscholar.org/paper/Learned-lessons-in-credit-card-fraud-detection-from-Pozzolo-Caelen/6d2e2a1caf5b3757ed0e8f404eabb31546d5698a. |
Prakash, "Quantum Algorithms for Linear Algebra and Machine Learning," Doctoral Thesis, Technical Report No. UCB/EECS-2014-211, University of California at Berkeley, 2014, pp. 1-9. |
Quattoni, A. et al., "Hidden Conditional Random Fields," IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(10), 2007, 6 pages. |
Rasmus, Antti , et al., "Semi-Supervised Learning with Ladder Networks", arXiv:1507.02672v2 [cs.NE] Nov. 24, 2015, 19 pages. |
Raymond , et al., "Systems and Methods for Comparing Entropy and KL Divergence of Post-Processed Samplers," U.S. Appl. No. 62/322,116, filed Apr. 13, 2016, 47 pages. |
Reed et al., "Training Deep Neural Networks on Noisy Labels with Bootstrapping," arXiv:1412.6596v3 [cs.CV] Apr. 15, 2015, 11 pages. |
Rezende , et al., "Stochastic Backpropagation and Approximate Inference in Deep Generative Models," arXiv:1401.4082v3 [stat.ML] May 30, 2014, 14 pages, https://arxiv.org/abs/1401.4082. |
Rezende et al., "Stochastic Backpropagation and Approximate Inference in Deep Generative Models," arXiv:1401.4082v3 [stat.ML] May 30, 2014, 14 pages. |
Rezende, Danilo J, et al., "Variational Inference with Normalizing Flows", Proceedings of the 32nd International Conference on Machine Learning, Lille, France 2015, JMLR: W&CP vol. 37, 9 pages. |
Rolfe , "Discrete variational autoencoders" arXiv:1609.02200 Apr. 22, 2017. https://arxiv.org/abs/1609.02200. |
Rolfe et al., "Discrete Variational Auto-Encoder Systems and Methods for Machine Learning Using Adiabatic Quantum Computers," U.S. Appl. No. 62/404,591, filed Oct. 5, 2016, 87 pages. |
Rolfe et al., "Discrete Variational Auto-Encoder Systems and Methods for Machine Learning Using Adiabatic Quantum Computers," U.S. Appl. No. 62/462,821, filed Feb. 23, 2017, 113 pages. |
Rolfe et al., "Systems and Methods for Machine Learning Using Adiabatic Quantum Computers," U.S. Appl. No. 62/207,057, filed Aug. 19, 2015, 39 pages. |
Rolfe, "Discrete Variational Auto-Encoder Systems and Methods for Machine Learning Using Adiabatic Quantum Computers," U.S. Appl. No. 62/206,974, filed Aug. 19, 2015, 43 pages. |
Rolfe, "Discrete Variational Auto-Encoder Systems and Methods for Machine Learning Using Adiabatic Quantum Computers," U.S. Appl. No. 62/268,321, filed Dec. 16, 2015, 52 pages. |
Rolfe, "Discrete Variational Auto-Encoder Systems and Methods for Machine Learning Using Adiabatic Quantum Computers," U.S. Appl. No. 62/307,929, filed Mar. 14, 2016, 67 pages. |
Rose , et al., "Systems and Methods for Quantum Processing of Data, for Example Functional Magnetic Resonance Image Data". U.S. Appl. No. 61/841,129, filed Jun. 28, 2013, 129 pages. |
Rose , et al., "Systems and Methods for Quantum Processing of Data, for Example Imaging Data". U.S. Appl. No. 61/873,303, filed Sep. 3, 2013, 38 pages. |
Rose , et al., "Training DBMs with Physical Neural Nets," Hack The Multiverse, Jan. 24, 2014, pp. 2-5. Retrieved from the Internet: URL: https://dwave.wordpress.com/2014/01/24/trainingdbmswith-physical-neural-nets, see pp. 2-5. |
Rose et al., "First ever DBM trained using a quantum computer", Hack the Multiverse, Programming quantum computers for fun and profit, XP-002743440, Jan. 6, 2014, 8 pages. |
Ross, S. et al., "Learning Message-Passing Inference Machines for Structured Prediction," CVPR 2011, 2011,8 pages. |
Sakkaris, et al., "QuDot Nets: Quantum Computers and Bayesian Networks", arXiv:1607.07887v1 [quant-ph] Jul. 26, 2016, 22 page. |
Salakhutdinov, R. & Murray, I., "On the quantitative analysis of deep belief networks", 2008. |
Salakhutdinov, R., "Learning deep Boltzmann machines using adaptive MCMC", 2010. |
Salakhutdinov, R., "Learning in Markov random transitions.elds using tempered", 2009. |
Saliman, Tim , "A Structured Variational Auto-encoder for Learning Deep Hierarchies of Sparse Features", arXiv:1602.08734v1 [stat.ML] Feb. 28, 2016, 3 pages. |
Salimans, Tim , et al., "Markov Chain Monte Carlo and Variational Inference: Bridging the Gap", arXiv:1410.6460v4 [stat.CO] May 19, 2015, 9 pages. |
Scarselli, F. et al., "The Graph Neural Network Model," IEEE Transactions on Neural Networks, vol. 20, No. 1,2009, 22 pages. |
Schulman , et al., "Gradient estimation using stochastic computing graphs". arXiv:1506.05254, Jan. 5, 2016. https://arxiv.org/abs/1506.05254. |
Schwartz-Ziv , et al., "Opening the black box of Deep Neural Networks via Information", arXiv:1703.00810 Apr. 29, 2017. https://arxiv.org/abs/1703.00810. |
Serban et al., "Multi-Modal Variational Encoder-Decoders" Dec. 1, 2016, arXiv: 1612.00377v1, pp. 1-18. (Year: 2016). |
Sethi, et al., "A revived survey of various credit card fraud detecion techniques", International Journal of Computer Science and Mobile Computing Apr. 14, 2014. https://tarjomefa.com/wp-content/uploads/2018/08/TarjomeFa-F994-English.pdf. |
Shah et al., "Feeling the Bern: Adaptive Estimators for Bernoulli Probabilities of Pairwise Comparisons" Mar. 22, 2016, pp. 1-33. Year: 2016). |
Shahriari, et al., "Taking the human out of the loop: A review of bayesian optimization", Proceedings of the IEEE 104 Jan. 1, 2016. |
Silver , et al., "Mastering the game of Go with deep neural networks and tree search". Nature, 529, 484489, 2016. |
Smelyanskiy , et al., "A near-term quantum computing approach for hard computational problems in space exploration" arXiv preprint arXir:1204.2821 (year:2012). |
Somma, R., S Boixo, and H Barnum. Quantum simulated annealing. arXiv preprint arXiv:0712.1008, 2007. |
Somma, RD, S Boixo, H Barnum, and E Knill. Quantum simulations of classical annealing processes. Physical review letters, 101(13):130504, 2008. |
Sonderby , et al., "Ladder Variational Autoencoders", arXiv:1602.02282v3 [stat.ML] May 27, 2016, 12 pages. |
Spall, "Multivariate Stochastic Approximation Using a Simultaneous Perturbation Gradient Approximation," IEEE Transactions on Automatic Control 37(3):332-341, 1992. |
Sprechmann , et al., "Dictionary learning and sparse coding for unsupervised clustering", in 2010 IEEE international conference on acoustics, speech and signal processing (pp. 2042-2045) IEEE (year:2010). |
Strub, F., et al. "Hybrid Collaborative Filtering with Autoencoders," arXiv:1603.00806v3 [cs.IR], Jul. 19, 2016, 10 pages. |
Sukhbaatar et al., "Training Convolutional Networks with Noisy Labels," arXiv:1406.2080v4 [cs.CV] Apr. 10, 2015, 11 pages. |
Sutton , "Learning to Predict by the Methods of Temporal Differences". https://webdocs.cs.ualberta.ca/ sutton/papers/sutton-88-with-erratum.pdf. |
Sutton, R., et al., "Policy gradient methods for reinforcement learning with function approximation". Advances in Neural Information Processing Sytems, 12, pp. 1057-1063, MIT Press, 2000. |
Suzuki, "Natural quantum reservoir computing for temporal information processing", Scientific Reports, Nature Portfolio, Jan. 25, 2022. |
Suzuki, et al., "Joint Multimodal Learning With Deep Generative Models", Nov. 7, 2016, arXiv:1611.0189v1 (Year: 2016). |
Szegedy , et al., "Rethinking the Inception Architecture for Computer Vision", 2016, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826 (Year: 2016). |
Tieleman, T. & Hinton, G. , "Using fast weights to improve persistent contrastive divergence", 2009. |
Tieleman, T., "Training Restricted Boltzmann Machines using Approximation to the Likelihood Gradient," ICML '08: Proceedings of the 25th international conference on Machine learning, 2008, 8 pages. |
Tokui, et al., "Evaluating the variance of likelihood-ratio gradient estimators", Proceedings of the 34th International Conference on Machine Learning, 2017. http://proceedings.mlr.press/v70/tokui17a.html. |
Tosh, Christopher, "Mixing Rates for the Alternating Gibbs Sampler over Restricted Boltzmann Machines and Friends" Jun. 2016. Year: 2016). |
Tripathi, et al., "Survey on credit card fraud detection methods", Internation Journal of Emerging Technology and Advanced Engineering Nov. 12, 2012. |
Tucci, "Use of a Quantum Computer to do Importance and Metropolis-Hastings Sampling of a Classical Bayesian Network", arXiv:0811.1792v1 [quant-ph] Nov. 12, 2008, 41 pages. |
Tucker , et al., "Rebar: Low-variance, unbiased gradient estimates for discrete latent variable models". arXiv:1703.07370, Nov. 6, 2017. https://arxiv.org/abs/1703.07370. |
Vahdat , "Machine Learning Systems and Methods for Training With Noisy Labels," U.S. Appl. No. 62/427,020, filed Nov. 28, 2016, 30 pages. |
Vahdat , "Machine Learning Systems and Methods for Training With Noisy Labels," U.S. Appl. No. 62/508,343, filed May 18, 2017, 46 pages. |
Vahdat , "Toward Robustness against Label Noise in Training Deep Disciminative Neural Networks". arXiv:1706.00038v2, Nov. 3, 2017. https://arxiv.org/abs/1706.00038. |
Vahdat , et al., "Dvae++: Discrete variational autoencoders with overlapping transformations", arXiv:1802.04920 May 25, 2018. https://arxiv.org/abs/1802.04920. |
Van Baalen, M. "Deep Matrix Factorization for Recommendation," Master's Thesis, Univ.of Amsterdam, Sep. 30, 2016, URL: https://scholar.google.co.kr/scholar?q=Deep+Matrix+Factorization+for+Recommendation&hl=ko&as_sdt=O&as_vis=l&oi=scholar, 99 pages. |
Van de Meent, J-W., Paige, B., & Wood, "Tempering by subsampling", 2014. |
Van der Maaten, L. et al., "Hidden-Unit Conditional Random Fields," Journal of Machine Learning Research 15, 2011, 10 Pages. |
Van Det Maaten , et al., "Hidden unit conditional random Fields". 14th International Conference on Artificial Intelligence and Statistics, 2011. |
Veit , et al., "Learning From Noisy Large-Scale Datasets With Minimal Supervision". arXiv:1701.01619v2, Apr. 10, 2017. https://arxiv.org/abs/1701.01619. |
Venkatesh, et al., "Quantum Fluctuation Theorems and Power Measurements," New J. Phys., 17, 2015, pp. 1-19. |
Wan, L., et al., "Regularization of Neural Networks using DropConnec". ICML 2013. |
Wang , et al., "Classification of common human diseases derived from shared genetic and environmental determinants", Nature Genetics Aug. 7, 2017. https://www.nature.com/articles/ng.3931. |
Wang et al., "Paired Restricted Boltzmann Machine for Linked Data" Oct. 2016. (Year: 2016). |
Wang, Discovering phase transitions with unsupervised learning, Physical Review B 94, 195105 (2016), 5 pages. |
Wang, W., Machta, J., & Katzgraber, H. G. "Population annealing: Theory and applications in spin glasses", 2015. |
Welling , et al., "Bayesian learning via stochastic gradient langevin dynamics", ICML Jun. 28, 2011. https://dl.acm.org/doi/10.5555/3104482.3104568. |
Wiebe, Nathan , et al., "Quantum Inspired Training for Boltzmann Machines", arXiv:1507.02642v1 [cs.LG] Jul. 9, 2015, 18 pages. |
Williams , "Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning," Springer, College of Computer Science, Northeastern University, Boston, MA, 1992, 27 pages, https://link.springer.com/article/10.1007/BF00992696. |
Williams, "Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning," College of Computer Science, Northeastern University, Boston, MA, 1992, 27 pages. |
Wittek, Peter , "What Can We Expect from Quantum Machine Learning". Yandex 1-32 School of Data Analysis Conference Machine Learning: Prospects and Applications, Oct. 5, 2015. pp. 1-16. |
Written Opinion of the International Searching Authority, dated Nov. 18, 2016, for International Application No. PCT/US2016/047627, 9 pages. |
Xiao , et al., "Learning from massive noisy labeled data for image classification". The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2015. |
Xie , et al., "A Theory of Generative ConvNet". ICML 2016. |
Xing , "Bayesian and Markov Networks: A unified view", Carnegie Mellon: School of Computer Science Sep. 19, 2007. http://www.cs.cmu.edu/˜epxing/Class/10708-07/Slides/lecture3-BN&MRF.pdf. |
Xu et Ou "Joint Stochastic Approximation Learning of Helmholtz Machines" Mar. 20, 2016, ICLR arXiv: 1603.06170v1, pp. 1-8. (Year: 2016). |
Yoshihara et al., "Estimating the Trend of Economic Indicators by Deep Learning", 2019-516164, Graduate School of System Informatics, Kobe University, 28 Annual Conferences of Japanese Society for Artificial Intelligence 2014, 10 pages. |
Zhang et al., "Understanding Deep Learning Requires Re-Thinking Generalization", arXiv:1611.03530 Feb. 26, 2017. https://arxiv.org/abs/1611.03530. |
Zhang, Yichuan , et al., "Continuous Relaxations for Discrete Hamiltonian Monte Carlo", School of Informatic, University of Edinburgh, Dept of Engineering, University of Cambridge, United Kingdom, 9 pages. |
Zhao et al., "Towards a Deeper Understanding of Variational Autoencoding Models", arXiv:1702.08658 Feb. 28, 2017. https://arxiv.org/abs/1702.08658. |
Zheng , et al., "Graph regularized sparse coding for image representation", IEEE transaction on image processing, 20(5), (Year: 2010) 1327-1336. |
Zhu, X. et al., "Combining Active Learning and Semi-Supervised Learning Using Gaussian Fields and Harmonic Functions," ICML 2003 workshop on The Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining, 2003, 8 pages. |
Zojaji et al., "A Survey of Credit Card Fraud Detection Techniques: Data and Technique Oriented Perspective", arXiv:1611.06439 Nov. 19, 2016. https://arxiv.org/abs/1611.06439. |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20220366288A1 (en) * | 2017-03-10 | 2022-11-17 | Rigetti & Co, Llc | Modular Control in a Quantum Computing System |
US11954562B2 (en) * | 2017-03-10 | 2024-04-09 | Rigetti & Co, Llc | Modular control in a quantum computing system |
US20200311525A1 (en) * | 2019-04-01 | 2020-10-01 | International Business Machines Corporation | Bias correction in deep learning systems |
US20220060235A1 (en) * | 2020-08-18 | 2022-02-24 | Qualcomm Incorporated | Federated learning for client-specific neural network parameter generation for wireless communication |
US11909482B2 (en) * | 2020-08-18 | 2024-02-20 | Qualcomm Incorporated | Federated learning for client-specific neural network parameter generation for wireless communication |
Also Published As
Publication number | Publication date |
---|---|
US20200193272A1 (en) | 2020-06-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11468293B2 (en) | Simulating and post-processing using a generative adversarial network | |
US11468262B2 (en) | Deep network embedding with adversarial regularization | |
US10922381B2 (en) | Re-equilibrated quantum sampling | |
US20220076131A1 (en) | Discrete variational auto-encoder systems and methods for machine learning using adiabatic quantum computers | |
US20200410384A1 (en) | Hybrid quantum-classical generative models for learning data distributions | |
CN110546656B (en) | Feedforward generation type neural network | |
US11410067B2 (en) | Systems and methods for machine learning using adiabatic quantum computers | |
CN111583263B (en) | Point cloud segmentation method based on joint dynamic graph convolution | |
CN100492399C (en) | Method for making human face posture estimation utilizing dimension reduction method | |
CN113112534B (en) | Three-dimensional biomedical image registration method based on iterative self-supervision | |
US20220108215A1 (en) | Robust and Data-Efficient Blackbox Optimization | |
Wang et al. | Thompson sampling via local uncertainty | |
CN113743474A (en) | Digital picture classification method and system based on cooperative semi-supervised convolutional neural network | |
US11625612B2 (en) | Systems and methods for domain adaptation | |
Bouchard et al. | Accelerating stochastic gradient descent via online learning to sample | |
Puente et al. | Convolutional restricted Boltzmann machine aided Monte Carlo: An application to Ising and Kitaev models | |
Nam et al. | Decoupled training for long-tailed classification with stochastic representations | |
US11481354B2 (en) | Systems and methods for calculating the ground state of non-diagonal Hamiltonians | |
US20210271867A1 (en) | Generative attribute optimization | |
EP1837807A1 (en) | Pattern recognition method | |
Orchard et al. | Bayesian inference in sparse gaussian graphical models | |
CN115131549A (en) | Significance target detection training method based on self-boosting learning | |
CN111310823B (en) | Target classification method, device and electronic system | |
CN113034473A (en) | Lung inflammation image target detection method based on Tiny-YOLOv3 | |
Wang | Generative Adversarial Networks (GAN): A Gentle Introduction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
FEPP | Fee payment procedure |
Free format text: ENTITY STATUS SET TO UNDISCOUNTED (ORIGINAL EVENT CODE: BIG.); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
AS | Assignment |
Owner name: D-WAVE SYSTEMS, INC., CANADA Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CHUDAK, FABIAN A.;REEL/FRAME:057125/0067 Effective date: 20190904 |
|
AS | Assignment |
Owner name: DWSI HOLDINGS INC., CANADA Free format text: MERGER AND CHANGE OF NAME;ASSIGNORS:D-WAVE SYSTEMS, INC.;DWSI HOLDINGS INC.;REEL/FRAME:057311/0298 Effective date: 20210101 Owner name: D-WAVE SYSTEMS, INC., CANADA Free format text: CONTINUATION;ASSIGNOR:D-WAVE SYSTEMS, INC.;REEL/FRAME:057311/0407 Effective date: 20201221 Owner name: DWSI HOLDINGS INC., CANADA Free format text: MERGER AND CHANGE OF NAME;ASSIGNORS:D-WAVE SYSTEMS, INC.;DWSI HOLDINGS INC.;DWSI HOLDINGS INC.;REEL/FRAME:057311/0298 Effective date: 20210101 Owner name: D-WAVE SYSTEMS, INC., CANADA Free format text: CHANGE OF NAME;ASSIGNOR:DWSI HOLDINGS INC.;REEL/FRAME:057285/0125 Effective date: 20210101 |
|
AS | Assignment |
Owner name: D-WAVE SYSTEMS INC., CANADA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE THE ASSIGNEE NAME PREVIOUSLY RECORDED AT REEL: 057285 FRAME: 0125. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT;ASSIGNOR:DWSI HOLDINGS INC.;REEL/FRAME:057575/0293 Effective date: 20210101 Owner name: DWSI HOLDINGS INC., CANADA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE FIRST ASSIGNOR'S NAME PREVIOUSLY RECORDED AT REEL: 057311 FRAME: 0298. ASSIGNOR(S) HEREBY CONFIRMS THE MERGER AND CHANGE OF NAME;ASSIGNORS:D-WAVE SYSTEMS INC.;DWSI HOLDINGS INC.;REEL/FRAME:057574/0952 Effective date: 20210101 Owner name: D-WAVE SYSTEMS INC., CANADA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE ASSIGNOR AND ASSIGNEE NAME PREVIOUSLY RECORDED AT REEL: 057311 FRAME: 0407. ASSIGNOR(S) HEREBY CONFIRMS THE CERTIFICATE OF CONTINUATION;ASSIGNOR:D-WAVE SYSTEMS INC.;REEL/FRAME:057574/0903 Effective date: 20201221 Owner name: D-WAVE SYSTEMS INC., CANADA Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE ASSIGNEE NAME PREVIOUSLY RECORDED AT REEL: 057125 FRAME: 0067. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT;ASSIGNOR:CHUDAK, FABIAN A.;REEL/FRAME:057574/0706 Effective date: 20190904 |
|
AS | Assignment |
Owner name: PSPIB UNITAS INVESTMENTS II INC., CANADA Free format text: SECURITY INTEREST;ASSIGNOR:D-WAVE SYSTEMS INC.;REEL/FRAME:059317/0871 Effective date: 20220303 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NOTICE OF ALLOWANCE MAILED -- APPLICATION RECEIVED IN OFFICE OF PUBLICATIONS |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT RECEIVED |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: PUBLICATIONS -- ISSUE FEE PAYMENT VERIFIED |
|
AS | Assignment |
Owner name: D-WAVE SYSTEMS INC., CANADA Free format text: RELEASE BY SECURED PARTY;ASSIGNOR:PSPIB UNITAS INVESTMENTS II INC., IN ITS CAPACITY AS COLLATERAL AGENT;REEL/FRAME:061493/0694 Effective date: 20220915 |
|
STCF | Information on status: patent grant |
Free format text: PATENTED CASE |
|
CC | Certificate of correction | ||
AS | Assignment |
Owner name: PSPIB UNITAS INVESTMENTS II INC., AS COLLATERAL AGENT, CANADA Free format text: INTELLECTUAL PROPERTY SECURITY AGREEMENT;ASSIGNORS:D-WAVE SYSTEMS INC.;1372934 B.C. LTD.;REEL/FRAME:063340/0888 Effective date: 20230413 |